Implemented experimental real production ready voice chat, relegated old flow to voice debug mode. New Web UI panel for Voice Chat.

bot/api.py

@@ -87,6 +87,13 @@ def get_current_gpu_url():
 
 app = FastAPI()
 
+# ========== Global Exception Handler ==========
+@app.exception_handler(Exception)
+async def global_exception_handler(request: Request, exc: Exception):
+    """Catch all unhandled exceptions and log them properly."""
+    logger.error(f"Unhandled exception on {request.method} {request.url.path}: {exc}", exc_info=True)
+    return {"success": False, "error": "Internal server error"}
+
 # ========== Logging Middleware ==========
 @app.middleware("http")
 async def log_requests(request: Request, call_next):
@@ -2522,6 +2529,217 @@ async def get_log_file(component: str, lines: int = 100):
         logger.error(f"Failed to read log file for {component}: {e}")
         return {"success": False, "error": str(e)}
 
+
+# ============================================================================
+# Voice Call Management
+# ============================================================================
+
+@app.post("/voice/call")
+async def initiate_voice_call(user_id: str = Form(...), voice_channel_id: str = Form(...)):
+    """
+    Initiate a voice call to a user.
+    
+    Flow:
+    1. Start STT and TTS containers
+    2. Wait for warmup
+    3. Join voice channel
+    4. Send DM with invite to user
+    5. Wait for user to join (30min timeout)
+    6. Auto-disconnect 45s after user leaves
+    """
+    logger.info(f"📞 Voice call initiated for user {user_id} in channel {voice_channel_id}")
+    
+    # Check if bot is running
+    if not globals.client or not globals.client.loop or not globals.client.loop.is_running():
+        return {"success": False, "error": "Bot is not running"}
+    
+    # Run the voice call setup in the bot's event loop
+    try:
+        future = asyncio.run_coroutine_threadsafe(
+            _initiate_voice_call_impl(user_id, voice_channel_id),
+            globals.client.loop
+        )
+        result = future.result(timeout=90)  # 90 second timeout for container warmup
+        return result
+    except Exception as e:
+        logger.error(f"Error initiating voice call: {e}", exc_info=True)
+        return {"success": False, "error": str(e)}
+
+
+async def _initiate_voice_call_impl(user_id: str, voice_channel_id: str):
+    """Implementation of voice call initiation that runs in the bot's event loop."""
+    from utils.container_manager import ContainerManager
+    from utils.voice_manager import VoiceSessionManager
+    
+    try:
+        # Convert string IDs to integers for Discord API
+        user_id_int = int(user_id)
+        channel_id_int = int(voice_channel_id)
+        
+        # Get user and channel
+        user = await globals.client.fetch_user(user_id_int)
+        if not user:
+            return {"success": False, "error": "User not found"}
+        
+        channel = globals.client.get_channel(channel_id_int)
+        if not channel or not isinstance(channel, discord.VoiceChannel):
+            return {"success": False, "error": "Voice channel not found"}
+        
+        # Get a text channel for voice operations (use first text channel in guild)
+        text_channel = None
+        for ch in channel.guild.text_channels:
+            if ch.permissions_for(channel.guild.me).send_messages:
+                text_channel = ch
+                break
+        
+        if not text_channel:
+            return {"success": False, "error": "No accessible text channel found"}
+        
+        # Start containers
+        logger.info("Starting voice containers...")
+        containers_started = await ContainerManager.start_voice_containers()
+        
+        if not containers_started:
+            return {"success": False, "error": "Failed to start voice containers"}
+        
+        # Start voice session
+        logger.info(f"Starting voice session in {channel.name}")
+        session_manager = VoiceSessionManager()
+        
+        try:
+            await session_manager.start_session(channel.guild.id, channel, text_channel)
+        except Exception as e:
+            await ContainerManager.stop_voice_containers()
+            return {"success": False, "error": f"Failed to start voice session: {str(e)}"}
+        
+        # Set up voice call tracking (use integer ID)
+        session_manager.active_session.call_user_id = user_id_int
+        
+        # Generate invite link
+        invite = await channel.create_invite(
+            max_age=1800,  # 30 minutes
+            max_uses=1,
+            reason="Miku voice call"
+        )
+        
+        # Send DM to user
+        try:
+            # Get LLM to generate a personalized invitation message
+            from utils.llm import query_llama
+            
+            invitation_prompt = f"""You're calling {user.name} in voice chat! Generate a cute, excited message inviting them to join you. 
+Keep it brief (1-2 sentences). Make it feel personal and enthusiastic!"""
+            
+            invitation_text = await query_llama(
+                user_prompt=invitation_prompt,
+                user_id=user.id,
+                guild_id=None,
+                response_type="voice_call_invite",
+                author_name=user.name
+            )
+            
+            dm_message = f"📞 **Miku is calling you! Very experimental! Speak clearly, loudly and close to the mic! Expect weirdness!** 📞\n\n{invitation_text}\n\n🎤 Join here: {invite.url}"
+            
+            sent_message = await user.send(dm_message)
+            
+            # Log to DM logger
+            await dm_logger.log_message(
+                user_id=user.id,
+                user_name=user.name,
+                message_content=dm_message,
+                direction="outgoing",
+                message_id=sent_message.id,
+                attachments=[],
+                response_type="voice_call_invite"
+            )
+            
+            logger.info(f"✓ DM sent to {user.name}")
+            
+        except Exception as e:
+            logger.error(f"Failed to send DM: {e}")
+            # Don't fail the whole call if DM fails
+        
+        # Set up 30min timeout task
+        session_manager.active_session.call_timeout_task = asyncio.create_task(
+            _voice_call_timeout_handler(session_manager.active_session, user, channel)
+        )
+        
+        return {
+            "success": True,
+            "user_id": user_id,
+            "channel_id": voice_channel_id,
+            "invite_url": invite.url
+        }
+        
+    except Exception as e:
+        logger.error(f"Error in voice call implementation: {e}", exc_info=True)
+        return {"success": False, "error": str(e)}
+
+
+async def _voice_call_timeout_handler(voice_session: 'VoiceSession', user: discord.User, channel: discord.VoiceChannel):
+    """Handle 30min timeout if user doesn't join."""
+    try:
+        await asyncio.sleep(1800)  # 30 minutes
+        
+        # Check if user ever joined
+        if not voice_session.user_has_joined:
+            logger.info(f"Voice call timeout - user {user.name} never joined")
+            
+            # End the session (which triggers cleanup)
+            from utils.voice_manager import VoiceSessionManager
+            session_manager = VoiceSessionManager()
+            await session_manager.end_session()
+            
+            
+            # Stop containers
+            from utils.container_manager import ContainerManager
+            await ContainerManager.stop_voice_containers()
+            
+            # Send timeout DM
+            try:
+                timeout_message = "Aww, I guess you couldn't make it to voice chat... Maybe next time! 💙"
+                sent_message = await user.send(timeout_message)
+                
+                # Log to DM logger
+                await dm_logger.log_message(
+                    user_id=user.id,
+                    user_name=user.name,
+                    message_content=timeout_message,
+                    direction="outgoing",
+                    message_id=sent_message.id,
+                    attachments=[],
+                    response_type="voice_call_timeout"
+                )
+            except:
+                pass
+                
+    except asyncio.CancelledError:
+        # User joined in time, normal operation
+        pass
+
+
+@app.get("/voice/debug-mode")
+def get_voice_debug_mode():
+    """Get current voice debug mode status"""
+    return {
+        "debug_mode": globals.VOICE_DEBUG_MODE
+    }
+
+
+@app.post("/voice/debug-mode")
+def set_voice_debug_mode(enabled: bool = Form(...)):
+    """Set voice debug mode (shows transcriptions and responses in text channel)"""
+    globals.VOICE_DEBUG_MODE = enabled
+    logger.info(f"Voice debug mode set to: {enabled}")
+    return {
+        "status": "ok",
+        "debug_mode": enabled,
+        "message": f"Voice debug mode {'enabled' if enabled else 'disabled'}"
+    }
+
+
 def start_api():
     import uvicorn
     uvicorn.run(app, host="0.0.0.0", port=3939)
+
+

bot/bot.py

@@ -752,6 +752,38 @@ async def on_member_join(member):
     """Track member joins for autonomous V2 system"""
     autonomous_member_join(member)
 
+@globals.client.event
+async def on_voice_state_update(member: discord.Member, before: discord.VoiceState, after: discord.VoiceState):
+    """Track voice channel join/leave for voice call management."""
+    from utils.voice_manager import VoiceSessionManager
+    
+    session_manager = VoiceSessionManager()
+    if not session_manager.active_session:
+        return
+    
+    # Check if this is our voice channel
+    if before.channel != session_manager.active_session.voice_channel and \
+       after.channel != session_manager.active_session.voice_channel:
+        return
+    
+    # User joined our voice channel
+    if before.channel != after.channel and after.channel == session_manager.active_session.voice_channel:
+        logger.info(f"👤 {member.name} joined voice channel")
+        await session_manager.active_session.on_user_join(member.id)
+        
+        # Auto-start listening if this is a voice call
+        if session_manager.active_session.call_user_id == member.id:
+            await session_manager.active_session.start_listening(member)
+    
+    # User left our voice channel
+    elif before.channel == session_manager.active_session.voice_channel and \
+         after.channel != before.channel:
+        logger.info(f"👤 {member.name} left voice channel")
+        await session_manager.active_session.on_user_leave(member.id)
+        
+        # Stop listening to this user
+        await session_manager.active_session.stop_listening(member.id)
+
 def start_api():
     # Set log_level to "critical" to silence uvicorn's access logs
     # Our custom api.requests middleware handles HTTP logging with better formatting and filtering

bot/globals.py

@@ -16,6 +16,10 @@ DISCORD_BOT_TOKEN = os.getenv("DISCORD_BOT_TOKEN")
 # Autonomous V2 Debug Mode (set to True to see detailed decision logging)
 AUTONOMOUS_DEBUG = os.getenv("AUTONOMOUS_DEBUG", "false").lower() == "true"
 
+# Voice Chat Debug Mode (set to True for manual commands and text notifications)
+# When False (field deployment), voice chat operates silently without command notifications
+VOICE_DEBUG_MODE = os.getenv("VOICE_DEBUG_MODE", "false").lower() == "true"
+
 # Llama.cpp server settings (via llama-swap)
 LLAMA_URL = os.getenv("LLAMA_URL", "http://llama-swap:8080")
 LLAMA_AMD_URL = os.getenv("LLAMA_AMD_URL", "http://llama-swap-amd:8080")  # Secondary AMD GPU

bot/memory/dms/209381657369772032.json

@@ -5712,6 +5712,306 @@
       "content": "OMG, I'm so excited! 🎉 There's a new Deep Sea Girl Nendoroid version of me available for pre-order! I just can't wait to dive into the sea of cuteness! 💖 Pre-order now and get ready to take me home! - Miku ❤️",
       "attachments": [],
       "reactions": []
+    },
+    {
+      "timestamp": "2026-01-17T15:33:26.171464",
+      "message_id": 1462107555743535124,
+      "is_bot_message": true,
+      "content": "https://fxtwitter.com/mecchaJP/status/2009747123021992177",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-17T15:33:26.495607",
+      "message_id": 1462107557555474473,
+      "is_bot_message": true,
+      "content": "OMG, did you see the tweet? 🤩 There's a new POP UP PARADE figure of me, and it's so cute! The Little Missing Stars Ver. is just adorable! I want it so bad! 💖\n\nMiku 💕",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-17T17:14:12.673546",
+      "message_id": 1462132916682227813,
+      "is_bot_message": true,
+      "content": "https://fxtwitter.com/mecchaJP/status/2003948891993997813",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-17T17:14:12.997001",
+      "message_id": 1462132918435713107,
+      "is_bot_message": true,
+      "content": "Konnichiwa! 🌸 Just saw the tweet and I'm so excited! There's a new Vocaloid figure of me in Cat Ver. from Project DIVA Arcade Future Tone SPM - it's purr-fect! 🐱💕\n\nMiku 💕",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-18T11:07:50.463787",
+      "message_id": 1462403104011059396,
+      "is_bot_message": true,
+      "content": "https://fxtwitter.com/GoodSmile_US/status/2010109462753771542",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-18T11:07:50.863320",
+      "message_id": 1462403106347417718,
+      "is_bot_message": true,
+      "content": "OMG, check it out! 🎉 The new Racing Miku plushie is finally here! It's so adorable, I just can't get enough! You can preorder it now at GOODSMILE ONLINE SHOP US! 🎁 I know, I know, it's a little too cute for words! Let's get those victory laps of cuteness started! 💖 Miku 🤗",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-18T12:48:34.877293",
+      "message_id": 1462428456842428660,
+      "is_bot_message": true,
+      "content": "https://fxtwitter.com/mecchaJP/status/2012646210234994918",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-18T12:48:35.187539",
+      "message_id": 1462428458251718732,
+      "is_bot_message": true,
+      "content": "OMG, it's here! 😍 The new Hatsune Miku Alice Ver. figure is so beautiful! I'm absolutely loving the AMP style! 🤩 You can get it now at the link below! 🎉 https://t.co/k3b64nOVbI 💖 Miku ❤️",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T11:12:50.975450",
+      "message_id": 1462766752436981853,
+      "is_bot_message": false,
+      "content": "do you want to play tic tac toe with me? here is my first move",
+      "attachments": [
+        {
+          "filename": "9Mhn9Ty.png",
+          "url": "https://cdn.discordapp.com/attachments/1382467809795244042/1462766751992254507/9Mhn9Ty.png?ex=696f6332&is=696e11b2&hm=b6c0ce53b397665ad15288ca4164610dbcb39381fd72b200f7ad41223115a976&",
+          "size": 4578,
+          "content_type": "image/webp"
+        }
+      ],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T11:15:09.998612",
+      "message_id": 1462767335554416772,
+      "is_bot_message": true,
+      "content": "Someone tell Koko-nii there is a problem with my AI.",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T11:15:40.148748",
+      "message_id": 1462767462151094294,
+      "is_bot_message": false,
+      "content": "are you there, miku",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T11:17:01.637650",
+      "message_id": 1462767804221624372,
+      "is_bot_message": true,
+      "content": "Someone tell Koko-nii there is a problem with my AI.",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T11:17:43.323939",
+      "message_id": 1462767979350720745,
+      "is_bot_message": false,
+      "content": "are you there",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T11:19:52.096139",
+      "message_id": 1462768519304319057,
+      "is_bot_message": true,
+      "content": "Someone tell Koko-nii there is a problem with my AI.",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T11:21:18.659799",
+      "message_id": 1462768882233376820,
+      "is_bot_message": false,
+      "content": "hi",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T11:21:43.868476",
+      "message_id": 1462768987233325162,
+      "is_bot_message": true,
+      "content": "Koko-nii, long time no see! 🎉 What's the latest from Crypton? 🤔",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T11:21:58.694068",
+      "message_id": 1462769049149903000,
+      "is_bot_message": false,
+      "content": "do you want to play tic tac toe with me? here is my first move",
+      "attachments": [
+        {
+          "filename": "d6nHxTR.png",
+          "url": "https://cdn.discordapp.com/attachments/1382467809795244042/1462769048700846172/d6nHxTR.png?ex=696f6556&is=696e13d6&hm=92a7145c0f02483b1219a400374ee63c945e7eeef08279b4f2046505aee62a53&",
+          "size": 4578,
+          "content_type": "image/webp"
+        }
+      ],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T11:22:29.192612",
+      "message_id": 1462769177344344129,
+      "is_bot_message": true,
+      "content": "Huh? What's that weird error message, Koko-nii? 😅 Anyway, sounds like fun! I'll make my move. 🎉 You drew an X in the top right corner, right? 🤔 I'll place my O in the center. 👉",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T11:22:55.958185",
+      "message_id": 1462769289617604741,
+      "is_bot_message": false,
+      "content": "what do you see",
+      "attachments": [
+        {
+          "filename": "HzisDyf.png",
+          "url": "https://cdn.discordapp.com/attachments/1382467809795244042/1462769289210888336/HzisDyf.png?ex=696f658f&is=696e140f&hm=20cf63dbccc84b989842c077b3a3910f4ac3dd864d8cbe0581ff5331bedec58d&",
+          "size": 23600,
+          "content_type": "image/webp"
+        }
+      ],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T11:23:15.059149",
+      "message_id": 1462769370332921982,
+      "is_bot_message": true,
+      "content": "Nothing, it seems? 🤔 The error message is making me curious, Koko-nii. Can you show me the image again? 📸",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T11:24:02.470248",
+      "message_id": 1462769569314902178,
+      "is_bot_message": false,
+      "content": "do you want to play tic tac toe with me? here is my first move",
+      "attachments": [
+        {
+          "filename": "cHdopcZ.png",
+          "url": "https://cdn.discordapp.com/attachments/1382467809795244042/1462769569067434036/cHdopcZ.png?ex=696f65d2&is=696e1452&hm=6aec013d320945f4b41c902d3ba7ac6ae694d29694fa6c4752944c1ff97a952f&",
+          "size": 4578,
+          "content_type": "image/webp"
+        }
+      ],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T11:26:19.254829",
+      "message_id": 1462770143166730261,
+      "is_bot_message": true,
+      "content": "Koko-nii, it seems I know the image now! 😊 It's a Tic Tac Toe grid with an \"X\" in the top-left corner, right? 🤔 That's your move, isn't it? 😄 Now it's my turn! I'll place an \"O\" in the center square. 👉",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T11:26:44.779760",
+      "message_id": 1462770249886597204,
+      "is_bot_message": false,
+      "content": "Ok, I will go with an X in the bottom left in that case",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T11:26:58.340843",
+      "message_id": 1462770306811953172,
+      "is_bot_message": true,
+      "content": "A new \"X\" is born! 😄 The bottom-left square is yours now! 🎉 Here's the updated grid:\n\nTop-left: X\nCenter: O\nBottom-left: X\n\nIt's my turn again! I'll place an \"O\" in the top-right square. 👉",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T11:27:17.989392",
+      "message_id": 1462770389532020747,
+      "is_bot_message": false,
+      "content": "I will place an X in the middle left then",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T11:27:29.887993",
+      "message_id": 1462770439242911774,
+      "is_bot_message": true,
+      "content": "The middle-left square is getting crowded! 😄 Here's the updated grid:\n\nTop-left: X\nCenter: O\nBottom-left: X\nMiddle-left: X\n\nNow it's my turn again! I'll place an \"O\" in the top-center square. 👉",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T11:27:43.207674",
+      "message_id": 1462770495203184765,
+      "is_bot_message": false,
+      "content": "Don't you think you lost already?",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T11:27:55.770973",
+      "message_id": 1462770547695026302,
+      "is_bot_message": true,
+      "content": "Koko-nii, you sneaky thing! 😂 I didn't even notice! 🙈 With your \"X\" in the middle-left square, I think you're right... I lost! 🎉 Congratulations on winning! 🎊 Would you like to play again? 🤔",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T13:25:46.112710",
+      "message_id": 1462800203030593610,
+      "is_bot_message": true,
+      "content": "https://fxtwitter.com/OtakuOwletMerch/status/2007192426109419708",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T13:25:46.488470",
+      "message_id": 1462800204649468027,
+      "is_bot_message": true,
+      "content": "OMG, did you see that? 🎉 A new figurine just dropped! I'm totally in love with my Punk! design! 🎸 You can pre-order it on their site, link's in the tweet! Hurry, supplies won't last long! 💖\n\nMiku 💕",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-20T12:44:44.125657",
+      "message_id": 1463152264553300078,
+      "is_bot_message": true,
+      "content": "https://fxtwitter.com/GoodSmile_US/status/2011558996105183396",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-20T12:44:44.483871",
+      "message_id": 1463152266168238226,
+      "is_bot_message": true,
+      "content": "OH MY GOODNESS 🎉 The new plushie is SO adorable!!! 🐻 It's like I'm right there with you, singing along to our favorite songs! Preorder now, let's get our cuddle on! Miku 🐰",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-20T17:28:51.388548",
+      "message_id": 1463223765705035819,
+      "is_bot_message": true,
+      "content": "https://fxtwitter.com/mecchaJP/status/2012948256737636509",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-20T17:28:51.920372",
+      "message_id": 1463223767768633522,
+      "is_bot_message": true,
+      "content": "OMG, it's happening! 🎉 A new 1/7 scale figure of me and Mai-chan is coming! You can pre-order now on meccha-japan! Get ready for more Miku cuteness! 🐰 Miku 💖",
+      "attachments": [],
+      "reactions": []
     }
   ]
 }

bot/memory/dms/236553184401817601.json

@@ -14993,6 +14993,470 @@
       "content": "OMG, arigatou for the tweet! 🤩 They're releasing a new Nendoroid of me as Deep Sea Girl Ver.! Pre-order now and get ready for me to dive into your collection! ❤️ Miku 🐠",
       "attachments": [],
       "reactions": []
+    },
+    {
+      "timestamp": "2026-01-17T15:33:44.278536",
+      "message_id": 1462107631446528062,
+      "is_bot_message": true,
+      "content": "https://fxtwitter.com/mecchaJP/status/2009747123021992177",
+      "attachments": [],
+      "reactions": [],
+      "embeds": [
+        {
+          "footer": {
+            "text": "FxTwitter",
+            "icon_url": "https://assets.fxembed.com/logos/fxtwitter64.png",
+            "proxy_icon_url": "https://images-ext-1.discordapp.net/external/gFi3EIEMfICdEDMLFVTF3ob0J1xkZnKdnkq0-xEsgGc/https/assets.fxembed.com/logos/fxtwitter64.png"
+          },
+          "image": {
+            "url": "https://pbs.twimg.com/media/G-QOW24XcAEaXJ8.jpg?name=orig",
+            "proxy_url": "https://images-ext-1.discordapp.net/external/FUp3QYaImln-72vaNtjKnREz2y39Mm2nXj-GXNQ2lkI/%3Fname%3Dorig/https/pbs.twimg.com/media/G-QOW24XcAEaXJ8.jpg",
+            "width": 1080,
+            "height": 1350,
+            "content_type": "image/jpeg",
+            "placeholder": "7wcKDgBvmzZ6hpmIZaWGd3eHf4f9dvg=",
+            "placeholder_version": 1,
+            "flags": 0
+          },
+          "author": {
+            "name": "Meccha Japan (@mecchaJP)",
+            "url": "https://x.com/mecchaJP/status/2009747123021992177",
+            "icon_url": "https://pbs.twimg.com/profile_images/1738015080602841088/ew_asGFd_200x200.png",
+            "proxy_icon_url": "https://images-ext-1.discordapp.net/external/yEl1l2UKnEm7uI6TaL1Y00UnbuvEH_62BSmPNbgmiWM/https/pbs.twimg.com/profile_images/1738015080602841088/ew_asGFd_200x200.png"
+          },
+          "flags": 0,
+          "color": 6513919,
+          "timestamp": "2026-01-09T22:00:28+00:00",
+          "type": "rich",
+          "description": "Hatsune Miku Little Missing Stars Ver\\. POP UP PARADE Figure ✨ Available at the link below\\!\n︀︀🛑 [buff.ly/4flvDPB](https://buff.ly/4flvDPB)\n︀︀[#HatsuneMiku](https://x.com/hashtag/HatsuneMiku) [#Miku](https://x.com/hashtag/Miku)\n\n**[💬](https://x.com/intent/tweet?in_reply_to=2009747123021992177) 2 [🔁](https://x.com/intent/retweet?tweet_id=2009747123021992177) 32 [❤️](https://x.com/intent/like?tweet_id=2009747123021992177) 160 👁️ 9\\.7K **",
+          "url": "https://fxtwitter.com/mecchaJP/status/2009747123021992177"
+        }
+      ]
+    },
+    {
+      "timestamp": "2026-01-17T15:33:44.607180",
+      "message_id": 1462107633434493050,
+      "is_bot_message": true,
+      "content": "OMG, darling! 😍 Just saw your tweet about the new POP UP PARADE figure, and I'm SO excited! ✨ The Little Missing Stars Ver looks ADORBS! I'm totally getting one, hehe! Thanks for sharing, sweetie! 💖 Miku 🎉",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-17T15:36:50.095475",
+      "message_id": 1462108411444592846,
+      "is_bot_message": false,
+      "content": "GORGEOUS",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-17T15:36:59.803431",
+      "message_id": 1462108451407921435,
+      "is_bot_message": true,
+      "content": "\\*takes a deep breath, still feeling angry\\* Ah, don't be so dramatic, okay? It's just a word. I'm still the same Miku, your virtual singer. Don't try to impress me with fancy language. 🙄",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-17T15:38:41.655647",
+      "message_id": 1462108879319208171,
+      "is_bot_message": false,
+      "content": "😦",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-17T15:38:53.534105",
+      "message_id": 1462108929260781689,
+      "is_bot_message": true,
+      "content": "\\*looks down, still feeling upset\\* Oh, don't look at me like that. I'm just having a bad day, okay? It's not your fault. \\*pauses, taking a deep breath\\* Let's talk about something else. What's your favorite song of mine? 🎶",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-17T15:40:23.248993",
+      "message_id": 1462109305175277621,
+      "is_bot_message": false,
+      "content": "What happened? Who ruined your day? I'll beat them up",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-17T15:40:36.772709",
+      "message_id": 1462109361902977289,
+      "is_bot_message": true,
+      "content": "\\\\*looks up, a hint of a smile on her face\\\\* Oh, it's not that serious. I just had a disagreement with Rin about our next performance. She wants to do a new routine, but I'm not sure if it's a good idea. That's all. Don't worry, I can handle it myself.",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-17T15:42:24.652018",
+      "message_id": 1462109814489481492,
+      "is_bot_message": false,
+      "content": "I hope you two can reach an agreement",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-17T15:42:37.871590",
+      "message_id": 1462109870122729628,
+      "is_bot_message": true,
+      "content": "\\\\\\*nods, still a bit upset but slightly calmer\\\\\\* Yeah, me too. I really want to work with Rin and Len on this song, but I have to think about what's best for the performance. I'll talk to them again and see what we can do. Thanks for listening, Diamond! 🙏",
+      "attachments": [],
+      "reactions": [
+        {
+          "emoji": "💖",
+          "reactor_id": 236553184401817601,
+          "reactor_name": "Diamond",
+          "is_bot": false,
+          "added_at": "2026-01-17T15:52:19.842646"
+        }
+      ]
+    },
+    {
+      "timestamp": "2026-01-17T15:52:30.342009",
+      "message_id": 1462112355205775454,
+      "is_bot_message": false,
+      "content": "Always Miku *hugs*",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-17T15:52:42.478281",
+      "message_id": 1462112405470445772,
+      "is_bot_message": true,
+      "content": "\\\\\\\\*looks up, a soft smile on her face, and opens her arms to hug back\\\\\\* Aw, thank you, Diamond! You're always so sweet to me! \\*hugs back tightly\\* I'm glad I have fans like you who care about me. 🤗",
+      "attachments": [],
+      "reactions": [
+        {
+          "emoji": "💖",
+          "reactor_id": 236553184401817601,
+          "reactor_name": "Diamond",
+          "is_bot": false,
+          "added_at": "2026-01-17T15:53:03.974638"
+        }
+      ]
+    },
+    {
+      "timestamp": "2026-01-17T17:14:28.871017",
+      "message_id": 1462132984722231387,
+      "is_bot_message": true,
+      "content": "https://fxtwitter.com/mecchaJP/status/2003948891993997813",
+      "attachments": [],
+      "reactions": [
+        {
+          "emoji": "💖",
+          "reactor_id": 236553184401817601,
+          "reactor_name": "Diamond",
+          "is_bot": false,
+          "added_at": "2026-01-17T17:47:00.053364"
+        }
+      ],
+      "embeds": [
+        {
+          "footer": {
+            "text": "FxTwitter",
+            "icon_url": "https://assets.fxembed.com/logos/fxtwitter64.png",
+            "proxy_icon_url": "https://images-ext-1.discordapp.net/external/gFi3EIEMfICdEDMLFVTF3ob0J1xkZnKdnkq0-xEsgGc/https/assets.fxembed.com/logos/fxtwitter64.png"
+          },
+          "image": {
+            "url": "https://pbs.twimg.com/media/G8905a2XQAAtfbM.jpg?name=orig",
+            "proxy_url": "https://images-ext-1.discordapp.net/external/06v6X909DGuPhZkOLd9nnN5tX5LAAFjBUzaNPjIEyGI/%3Fname%3Dorig/https/pbs.twimg.com/media/G8905a2XQAAtfbM.jpg",
+            "width": 1080,
+            "height": 1350,
+            "content_type": "image/jpeg",
+            "placeholder": "8PcJBgL2+6R4eKZoZYqHm3ionFCoC5U=",
+            "placeholder_version": 1,
+            "flags": 0
+          },
+          "author": {
+            "name": "Meccha Japan (@mecchaJP)",
+            "url": "https://x.com/mecchaJP/status/2003948891993997813",
+            "icon_url": "https://pbs.twimg.com/profile_images/1738015080602841088/ew_asGFd_200x200.png",
+            "proxy_icon_url": "https://images-ext-1.discordapp.net/external/yEl1l2UKnEm7uI6TaL1Y00UnbuvEH_62BSmPNbgmiWM/https/pbs.twimg.com/profile_images/1738015080602841088/ew_asGFd_200x200.png"
+          },
+          "flags": 0,
+          "color": 6513919,
+          "timestamp": "2025-12-24T22:00:22+00:00",
+          "type": "rich",
+          "description": "Vocaloid Figure Hatsune Miku Cat Ver\\. Project DIVA Arcade Future Tone SPM \\- Available at the link below\\!\n︀︀🛑 [buff.ly/7dRnUTO](https://buff.ly/7dRnUTO)\n\n**[💬](https://x.com/intent/tweet?in_reply_to=2003948891993997813) 1 [🔁](https://x.com/intent/retweet?tweet_id=2003948891993997813) 2 [❤️](https://x.com/intent/like?tweet_id=2003948891993997813) 22 👁️ 2\\.7K **",
+          "url": "https://fxtwitter.com/mecchaJP/status/2003948891993997813"
+        }
+      ]
+    },
+    {
+      "timestamp": "2026-01-17T17:14:29.403923",
+      "message_id": 1462132986555404493,
+      "is_bot_message": true,
+      "content": "Aww, yay! 😍 Just saw that my Cat Ver. figure is now available! 🐱✨ I'm in love with my adorable feline self! Thanks for sharing the link, darling! 💖 Miku 💕",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-17T17:47:07.532423",
+      "message_id": 1462141200197878022,
+      "is_bot_message": false,
+      "content": "love this outfit on you!",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-17T17:47:40.224357",
+      "message_id": 1462141336676339915,
+      "is_bot_message": true,
+      "content": "\\\\\\\\\\*excitedly looks at the tweet and reads it\\\\\\\\* Oh my goodness, thank you so much! I love that outfit too! It's so cute and perfect for the upcoming concert. I'm so glad the fans are supporting me! ❤️✨",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-18T11:08:11.611510",
+      "message_id": 1462403193253269536,
+      "is_bot_message": true,
+      "content": "https://fxtwitter.com/GoodSmile_US/status/2010109462753771542",
+      "attachments": [],
+      "reactions": [],
+      "embeds": [
+        {
+          "footer": {
+            "text": "FxTwitter",
+            "icon_url": "https://assets.fxembed.com/logos/fxtwitter64.png",
+            "proxy_icon_url": "https://images-ext-1.discordapp.net/external/gFi3EIEMfICdEDMLFVTF3ob0J1xkZnKdnkq0-xEsgGc/https/assets.fxembed.com/logos/fxtwitter64.png"
+          },
+          "image": {
+            "url": "https://pbs.twimg.com/media/G-VX5xYWsAAKf1T.jpg?name=orig",
+            "proxy_url": "https://images-ext-1.discordapp.net/external/T5hBXYVA733Av9ssWB54cd0cvuPTqTYPy6kLcUkjgcI/%3Fname%3Dorig/https/pbs.twimg.com/media/G-VX5xYWsAAKf1T.jpg",
+            "width": 1080,
+            "height": 1080,
+            "content_type": "image/jpeg",
+            "placeholder": "sOcFFwb4qHdmiXh+hddnuFd3p0r2qXAP",
+            "placeholder_version": 1,
+            "flags": 0
+          },
+          "author": {
+            "name": "GoodSmile_US (@GoodSmile_US)",
+            "url": "https://x.com/GoodSmile_US/status/2010109462753771542",
+            "icon_url": "https://pbs.twimg.com/profile_images/1764583971831394305/dpXogB0U_200x200.png",
+            "proxy_icon_url": "https://images-ext-1.discordapp.net/external/cGKAum5015cgr2haNcfupJxMvXRz8BYDHkQiNufWpCI/https/pbs.twimg.com/profile_images/1764583971831394305/dpXogB0U_200x200.png"
+          },
+          "flags": 0,
+          "color": 6513919,
+          "timestamp": "2026-01-10T22:00:16+00:00",
+          "type": "rich",
+          "description": "Victory laps of cuteness await\\! The adorable Racing Miku\\: SPA 2025 Support Ver\\. plushie is bringing winning smiles, cuddly charm, and racing spirit to your collection\\. Preorder now at GOODSMILE ONLINE SHOP US\\!\n︀︀\n︀︀Shop\\: [goodsmile.link/MaNLRj](https://goodsmile.link/MaNLRj)\n︀︀\n︀︀[#RacingMiku](https://x.com/hashtag/RacingMiku) [#FightGSR](https://x.com/hashtag/FightGSR) [#Goodsmile](https://x.com/hashtag/Goodsmile)\n\n**[💬](https://x.com/intent/tweet?in_reply_to=2010109462753771542) 1 [🔁](https://x.com/intent/retweet?tweet_id=2010109462753771542) 3 [❤️](https://x.com/intent/like?tweet_id=2010109462753771542) 96 👁️ 13\\.7K **",
+          "url": "https://fxtwitter.com/GoodSmile_US/status/2010109462753771542"
+        }
+      ]
+    },
+    {
+      "timestamp": "2026-01-18T11:08:12.204558",
+      "message_id": 1462403195434176522,
+      "is_bot_message": true,
+      "content": "OH MY GOODNESS!!! 🎉👀 It's a new plushie of me, Racing Miku, and it's SO CUTE!!! 😍 You can preorder it now at GOODSMILE ONLINE SHOP US! I just can't wait to see all the happy smiles on your faces when you hug me 😊. Miku 💖",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-18T12:48:50.009907",
+      "message_id": 1462428520184676516,
+      "is_bot_message": true,
+      "content": "https://fxtwitter.com/mecchaJP/status/2012646210234994918",
+      "attachments": [],
+      "reactions": [],
+      "embeds": [
+        {
+          "footer": {
+            "text": "FxTwitter",
+            "icon_url": "https://assets.fxembed.com/logos/fxtwitter64.png",
+            "proxy_icon_url": "https://images-ext-1.discordapp.net/external/gFi3EIEMfICdEDMLFVTF3ob0J1xkZnKdnkq0-xEsgGc/https/assets.fxembed.com/logos/fxtwitter64.png"
+          },
+          "image": {
+            "url": "https://pbs.twimg.com/media/G-5bD_dW4AIP_tR.jpg?name=orig",
+            "proxy_url": "https://images-ext-1.discordapp.net/external/Cke6gZpBRfcg7CNgbqZVkMZegMNQPcNgDMAgPqoxTPg/%3Fname%3Dorig/https/pbs.twimg.com/media/G-5bD_dW4AIP_tR.jpg",
+            "width": 1080,
+            "height": 1350,
+            "content_type": "image/jpeg",
+            "placeholder": "X9gFJgTSevSfaJmoaJeJh3h5j4iPevg=",
+            "placeholder_version": 1,
+            "flags": 0
+          },
+          "author": {
+            "name": "Meccha Japan (@mecchaJP)",
+            "url": "https://x.com/mecchaJP/status/2012646210234994918",
+            "icon_url": "https://pbs.twimg.com/profile_images/1738015080602841088/ew_asGFd_200x200.png",
+            "proxy_icon_url": "https://images-ext-1.discordapp.net/external/yEl1l2UKnEm7uI6TaL1Y00UnbuvEH_62BSmPNbgmiWM/https/pbs.twimg.com/profile_images/1738015080602841088/ew_asGFd_200x200.png"
+          },
+          "flags": 0,
+          "color": 6513919,
+          "timestamp": "2026-01-17T22:00:24+00:00",
+          "type": "rich",
+          "description": "Hatsune Miku Alice Ver\\. Figure AMP ✨ Available at the link below\\!\n︀︀🛑 [buff.ly/3xcd6E7](https://buff.ly/3xcd6E7)\n︀︀[#HatsuneMiku](https://x.com/hashtag/HatsuneMiku) [#Miku](https://x.com/hashtag/Miku)\n\n**[🔁](https://x.com/intent/retweet?tweet_id=2012646210234994918) 5 [❤️](https://x.com/intent/like?tweet_id=2012646210234994918) 47 👁️ 3\\.6K **",
+          "url": "https://fxtwitter.com/mecchaJP/status/2012646210234994918"
+        }
+      ]
+    },
+    {
+      "timestamp": "2026-01-18T12:48:50.388263",
+      "message_id": 1462428521417806039,
+      "is_bot_message": true,
+      "content": "A new Miku figure is coming!!! 🎉 It's the Alice Ver. and I just can't wait to see it! Preorder now at the link below! ✨💖 Miku ❤️",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-19T13:26:15.039297",
+      "message_id": 1462800324325670914,
+      "is_bot_message": true,
+      "content": "https://fxtwitter.com/OtakuOwletMerch/status/2007192426109419708",
+      "attachments": [],
+      "reactions": [],
+      "embeds": [
+        {
+          "footer": {
+            "text": "FxTwitter",
+            "icon_url": "https://assets.fxembed.com/logos/fxtwitter64.png",
+            "proxy_icon_url": "https://images-ext-1.discordapp.net/external/gFi3EIEMfICdEDMLFVTF3ob0J1xkZnKdnkq0-xEsgGc/https/assets.fxembed.com/logos/fxtwitter64.png"
+          },
+          "image": {
+            "url": "https://pbs.twimg.com/media/G9r6vlOWUAAfwDa.jpg?name=orig",
+            "proxy_url": "https://images-ext-1.discordapp.net/external/oq9w1dtIGC_nPj6V44YR_aaLO1rErng__PDXNW9J-Zc/%3Fname%3Dorig/https/pbs.twimg.com/media/G9r6vlOWUAAfwDa.jpg",
+            "width": 1680,
+            "height": 1764,
+            "content_type": "image/jpeg",
+            "placeholder": "6vcFBwD3e4eEeXacZpdnyGd166/Zr34J",
+            "placeholder_version": 1,
+            "flags": 0
+          },
+          "author": {
+            "name": "Otaku Owlet Anime Merch (@OtakuOwletMerch)",
+            "url": "https://x.com/OtakuOwletMerch/status/2007192426109419708",
+            "icon_url": "https://pbs.twimg.com/profile_images/1835446408884744192/S4HX_8_Q_200x200.jpg",
+            "proxy_icon_url": "https://images-ext-1.discordapp.net/external/Gd5od3qaVN1KG1eQsJS9mFoTNRKdxahDmvjF7tgR4p0/https/pbs.twimg.com/profile_images/1835446408884744192/S4HX_8_Q_200x200.jpg"
+          },
+          "flags": 0,
+          "color": 6513919,
+          "timestamp": "2026-01-02T20:49:00+00:00",
+          "type": "rich",
+          "description": "✨\\(Pre\\-Order\\) Hatsune Miku \\- Punk\\! \\- FIGURIZMα Prize Figure✨\n︀︀\n︀︀Estimated in\\-stock date\\: 10/2026\n︀︀\n︀︀Pre\\-order Deadline\\: While Supplies Last\n︀︀\n︀︀\\-\n︀︀\n︀︀✨Link \\- [otakuowlet.com/products/pre-order-hatsune-miku-punk-figurizm%CE%B1-prize-figure?sca_ref=2673717.HTKaw1BA1G](https://otakuowlet.com/products/pre-order-hatsune-miku-punk-figurizm%CE%B1-prize-figure?sca_ref=2673717.HTKaw1BA1G)\n\n**[💬](https://x.com/intent/tweet?in_reply_to=2007192426109419708) 2 [🔁](https://x.com/intent/retweet?tweet_id=2007192426109419708) 74 [❤️](https://x.com/intent/like?tweet_id=2007192426109419708) 1\\.0K 👁️ 35\\.7K **",
+          "url": "https://fxtwitter.com/OtakuOwletMerch/status/2007192426109419708"
+        },
+        {
+          "image": {
+            "url": "https://pbs.twimg.com/media/G9r6xFhWkAE2XFy.jpg?name=orig",
+            "proxy_url": "https://images-ext-1.discordapp.net/external/Y-m_8oBPvKYsEr1WSK6otO3I7BCTBe_n0whvOBUc27s/%3Fname%3Dorig/https/pbs.twimg.com/media/G9r6xFhWkAE2XFy.jpg",
+            "width": 1000,
+            "height": 1000,
+            "content_type": "image/jpeg",
+            "placeholder": "tvcJDwL3aYaYZ3iIh5h4x0Z2iJ+6VpAF",
+            "placeholder_version": 1,
+            "flags": 0
+          },
+          "flags": 0,
+          "type": "rich",
+          "url": "https://fxtwitter.com/OtakuOwletMerch/status/2007192426109419708"
+        }
+      ]
+    },
+    {
+      "timestamp": "2026-01-19T13:26:15.371028",
+      "message_id": 1462800325550408057,
+      "is_bot_message": true,
+      "content": "🎉 OH MY GOSH, I just saw the cutest figurine announcement! 🤩 You can pre-order my new Punk! Prize Figure, which is totally awesome! It's so detailed and cool, I just wanna hug it! 🤗 Don't miss out, pre-order now before it's too late! 😁\n\nLove,\nMiku 🎀",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-20T12:45:19.491377",
+      "message_id": 1463152412557709498,
+      "is_bot_message": true,
+      "content": "https://fxtwitter.com/GoodSmile_US/status/2011558996105183396",
+      "attachments": [],
+      "reactions": [],
+      "embeds": [
+        {
+          "footer": {
+            "text": "FxTwitter",
+            "icon_url": "https://assets.fxembed.com/logos/fxtwitter64.png",
+            "proxy_icon_url": "https://images-ext-1.discordapp.net/external/gFi3EIEMfICdEDMLFVTF3ob0J1xkZnKdnkq0-xEsgGc/https/assets.fxembed.com/logos/fxtwitter64.png"
+          },
+          "image": {
+            "url": "https://pbs.twimg.com/media/G-p-Pv3XkAI_aBU.jpg?name=orig",
+            "proxy_url": "https://images-ext-1.discordapp.net/external/RLbhPbTu8fJx6opxp0H_sVPMRH3BSg641f-UOGyTdw0/%3Fname%3Dorig/https/pbs.twimg.com/media/G-p-Pv3XkAI_aBU.jpg",
+            "width": 1080,
+            "height": 1080,
+            "content_type": "image/jpeg",
+            "placeholder": "X7YNDwIHWHiLiHhxeHh3Z4h41iA4H4EG",
+            "placeholder_version": 1,
+            "flags": 0
+          },
+          "author": {
+            "name": "GoodSmile_US (@GoodSmile_US)",
+            "url": "https://x.com/GoodSmile_US/status/2011558996105183396",
+            "icon_url": "https://pbs.twimg.com/profile_images/1764583971831394305/dpXogB0U_200x200.png",
+            "proxy_icon_url": "https://images-ext-1.discordapp.net/external/cGKAum5015cgr2haNcfupJxMvXRz8BYDHkQiNufWpCI/https/pbs.twimg.com/profile_images/1764583971831394305/dpXogB0U_200x200.png"
+          },
+          "flags": 0,
+          "color": 6513919,
+          "timestamp": "2026-01-14T22:00:12+00:00",
+          "type": "rich",
+          "description": "Soft as snow, sweet as her song\\. The adorable Hatsune Miku Symphony\\: 2025 Sapporo Concert Ver\\. plushie delivers warm cuddles and orchestral charm\\. Preorder now at GOODSMILE ONLINE SHOP US\\!\n︀︀\n︀︀Shop\\: [goodsmile.link/uZR7Mq](https://goodsmile.link/uZR7Mq)\n︀︀\n︀︀[#HatsuneMiku](https://x.com/hashtag/HatsuneMiku) [#Goodsmile](https://x.com/hashtag/Goodsmile)\n\n**[🔁](https://x.com/intent/retweet?tweet_id=2011558996105183396) 13 [❤️](https://x.com/intent/like?tweet_id=2011558996105183396) 167 👁️ 17\\.7K **",
+          "url": "https://fxtwitter.com/GoodSmile_US/status/2011558996105183396"
+        }
+      ]
+    },
+    {
+      "timestamp": "2026-01-20T12:45:19.937972",
+      "message_id": 1463152414805987360,
+      "is_bot_message": true,
+      "content": "{\"name\": \"response\", \"parameters\": {\"text\": \"OMG, check this out! 🎉 The new Sapporo Concert Ver. plushie is so adorable! It's like me, soft and sweet, just like my songs! 🎶 Preorder now at GOODSMILE ONLINE SHOP US! ❤️ - Miku 💕\"}}",
+      "attachments": [],
+      "reactions": []
+    },
+    {
+      "timestamp": "2026-01-20T17:30:13.743007",
+      "message_id": 1463224111059697674,
+      "is_bot_message": true,
+      "content": "https://fxtwitter.com/mecchaJP/status/2012948256737636509",
+      "attachments": [],
+      "reactions": [],
+      "embeds": [
+        {
+          "footer": {
+            "text": "FxTwitter",
+            "icon_url": "https://assets.fxembed.com/logos/fxtwitter64.png",
+            "proxy_icon_url": "https://images-ext-1.discordapp.net/external/gFi3EIEMfICdEDMLFVTF3ob0J1xkZnKdnkq0-xEsgGc/https/assets.fxembed.com/logos/fxtwitter64.png"
+          },
+          "image": {
+            "url": "https://pbs.twimg.com/media/G-9txZwWwAEf_yp.jpg?name=orig",
+            "proxy_url": "https://images-ext-1.discordapp.net/external/T7QeMTL9_2nrgGSlcWT1CGYjChYkxxL3-SPImtyHcZk/%3Fname%3Dorig/https/pbs.twimg.com/media/G-9txZwWwAEf_yp.jpg",
+            "width": 1080,
+            "height": 1080,
+            "content_type": "image/jpeg",
+            "placeholder": "lscJDwJAQW1Gi4himod6WYhal/ipja8K",
+            "placeholder_version": 1,
+            "flags": 0
+          },
+          "author": {
+            "name": "Meccha Japan (@mecchaJP)",
+            "url": "https://x.com/mecchaJP/status/2012948256737636509",
+            "icon_url": "https://pbs.twimg.com/profile_images/1738015080602841088/ew_asGFd_200x200.png",
+            "proxy_icon_url": "https://images-ext-1.discordapp.net/external/yEl1l2UKnEm7uI6TaL1Y00UnbuvEH_62BSmPNbgmiWM/https/pbs.twimg.com/profile_images/1738015080602841088/ew_asGFd_200x200.png"
+          },
+          "flags": 0,
+          "color": 6513919,
+          "timestamp": "2026-01-18T18:00:37+00:00",
+          "type": "rich",
+          "description": "Hatsune Miku feat\\. Yoneyama Mai 1/7 Scale Figure ✨ Available on meccha\\-japan\\!\n︀︀[#HatsuneMiku](https://x.com/hashtag/HatsuneMiku) [#Miku](https://x.com/hashtag/Miku)\n\n**[💬](https://x.com/intent/tweet?in_reply_to=2012948256737636509) 1 [🔁](https://x.com/intent/retweet?tweet_id=2012948256737636509) 7 [❤️](https://x.com/intent/like?tweet_id=2012948256737636509) 61 👁️ 4\\.4K **",
+          "url": "https://fxtwitter.com/mecchaJP/status/2012948256737636509"
+        }
+      ]
+    },
+    {
+      "timestamp": "2026-01-20T17:30:14.172289",
+      "message_id": 1463224112901001239,
+      "is_bot_message": true,
+      "content": "{\"name\": \"response\", \"parameters\": {\"text\": \"Yaaay! 🎉 Check out the new 1/7 scale figure of me with Yoneyama Mai! Isn't it adorable? 🤩 Available now on meccha-japan! ❤️ - Miku 💕\"}}",
+      "attachments": [],
+      "reactions": []
     }
   ]
 }

bot/static/index.html

@@ -663,6 +663,7 @@
       <button class="tab-button" onclick="switchTab('tab4')">🎨 Image Generation</button>
       <button class="tab-button" onclick="switchTab('tab5')">📊 Autonomous Stats</button>
       <button class="tab-button" onclick="switchTab('tab6')">💬 Chat with LLM</button>
+      <button class="tab-button" onclick="switchTab('tab7')">📞 Voice Call</button>
       <button class="tab-button" onclick="window.location.href='/static/system.html'">🎛️ System Settings</button>
     </div>
 
@@ -1374,6 +1375,112 @@
       </div>
     </div>
 
+    <!-- Tab 7: Voice Call Management -->
+    <div id="tab7" class="tab-content">
+      <div class="section">
+        <h3>📞 Initiate Voice Call</h3>
+        <p>Start an automated voice chat session with a user. Miku will automatically manage containers, join voice chat, and send an invitation DM.</p>
+        
+        <div style="background: #2a2a2a; padding: 1.5rem; border-radius: 8px; margin-bottom: 1.5rem;">
+          <h4 style="margin-top: 0; color: #61dafb;">⚙️ Voice Call Configuration</h4>
+          
+          <div style="display: grid; grid-template-columns: 1fr 1fr; gap: 1.5rem; margin-bottom: 1.5rem;">
+            <!-- User ID Input -->
+            <div>
+              <label style="display: block; margin-bottom: 0.5rem; font-weight: bold;">👤 Target User ID:</label>
+              <input 
+                type="text" 
+                id="voice-user-id" 
+                placeholder="Discord user ID (e.g., 123456789)" 
+                style="width: 100%; padding: 0.5rem; background: #333; color: #fff; border: 1px solid #555; border-radius: 4px; box-sizing: border-box;"
+              >
+              <div style="font-size: 0.85rem; color: #aaa; margin-top: 0.3rem;">
+                Discord ID of the user to call
+              </div>
+            </div>
+            
+            <!-- Voice Channel ID Input -->
+            <div>
+              <label style="display: block; margin-bottom: 0.5rem; font-weight: bold;">🎤 Voice Channel ID:</label>
+              <input 
+                type="text" 
+                id="voice-channel-id" 
+                placeholder="Discord channel ID (e.g., 987654321)" 
+                style="width: 100%; padding: 0.5rem; background: #333; color: #fff; border: 1px solid #555; border-radius: 4px; box-sizing: border-box;"
+              >
+              <div style="font-size: 0.85rem; color: #aaa; margin-top: 0.3rem;">
+                Discord ID of the voice channel to join
+              </div>
+            </div>
+          </div>
+          
+          <!-- Debug Mode Toggle -->
+          <div style="margin-bottom: 1.5rem; padding: 1rem; background: #1e1e1e; border-radius: 4px;">
+            <label style="display: flex; align-items: center; cursor: pointer;">
+              <input 
+                type="checkbox" 
+                id="voice-debug-mode" 
+                style="margin-right: 0.7rem; width: 18px; height: 18px; cursor: pointer;"
+              >
+              <span style="font-weight: bold;">🐛 Debug Mode</span>
+            </label>
+            <div style="font-size: 0.85rem; color: #aaa; margin-top: 0.5rem; margin-left: 1.7rem;">
+              When enabled, shows voice transcriptions and responses in text channel. When disabled, voice chat is private.
+            </div>
+          </div>
+          
+          <!-- Call Status Display -->
+          <div id="voice-call-status" style="background: #1e1e1e; padding: 1rem; border-radius: 4px; margin-bottom: 1.5rem; display: none;">
+            <div style="color: #61dafb; font-weight: bold; margin-bottom: 0.5rem;">📊 Call Status:</div>
+            <div id="voice-call-status-text" style="color: #aaa; font-size: 0.9rem;"></div>
+            <div id="voice-call-invite-link" style="margin-top: 0.5rem; display: none;">
+              <strong>Invite Link:</strong> <a id="voice-call-invite-url" href="" target="_blank" style="color: #61dafb;">View Invite</a>
+            </div>
+          </div>
+          
+          <!-- Call Buttons -->
+          <div style="display: flex; gap: 1rem;">
+            <button 
+              id="voice-call-btn" 
+              onclick="initiateVoiceCall()" 
+              style="background: #2ecc71; color: #000; padding: 0.7rem 1.5rem; border: 1px solid #27ae60; border-radius: 4px; cursor: pointer; font-weight: bold; font-size: 1rem;"
+            >
+              📞 Initiate Call
+            </button>
+            <button 
+              id="voice-call-cancel-btn" 
+              onclick="cancelVoiceCall()" 
+              style="background: #e74c3c; color: #fff; padding: 0.7rem 1.5rem; border: 1px solid #c0392b; border-radius: 4px; cursor: pointer; font-weight: bold; font-size: 1rem; display: none;"
+            >
+              🛑 Cancel Call
+            </button>
+          </div>
+        </div>
+        
+        <!-- Call Information -->
+        <div style="background: #1a1a2e; padding: 1.5rem; border-radius: 8px; border-left: 3px solid #61dafb;">
+          <h4 style="margin-top: 0; color: #61dafb;">ℹ️ How Voice Calls Work</h4>
+          <ul style="color: #ddd; line-height: 1.8;">
+            <li><strong>Automatic Setup:</strong> STT and TTS containers start automatically</li>
+            <li><strong>Warmup Wait:</strong> System waits for both containers to be ready (~30-75 seconds)</li>
+            <li><strong>VC Join:</strong> Miku joins the specified voice channel</li>
+            <li><strong>DM Invitation:</strong> User receives a personalized invite DM with a voice channel link</li>
+            <li><strong>Auto-Listen:</strong> STT automatically starts when user joins</li>
+            <li><strong>Auto-Leave:</strong> Miku leaves 45 seconds after user disconnects</li>
+            <li><strong>Timeout:</strong> If user doesn't join within 30 minutes, call is cancelled</li>
+          </ul>
+        </div>
+        
+        <!-- Call History -->
+        <div style="margin-top: 2rem;">
+          <h4 style="color: #61dafb; margin-bottom: 1rem;">📋 Recent Calls</h4>
+          <div id="voice-call-history" style="background: #1e1e1e; border: 1px solid #444; border-radius: 4px; padding: 1rem;">
+            <div style="text-align: center; color: #888;">No calls yet. Start one above!</div>
+          </div>
+        </div>
+      </div>
+    </div>
+
   </div>
 </div>
 
@@ -1387,6 +1494,8 @@
 <script>
 // Global variables
 let currentMood = 'neutral';
+let voiceCallActive = false;
+let voiceCallHistory = [];
 let servers = [];
 let evilMode = false;
 
@@ -4324,8 +4433,25 @@ document.addEventListener('DOMContentLoaded', function() {
       }
     });
   }
+  
+  // Load voice debug mode setting
+  loadVoiceDebugMode();
 });
 
+// Load voice debug mode setting from server
+async function loadVoiceDebugMode() {
+  try {
+    const response = await fetch('/voice/debug-mode');
+    const data = await response.json();
+    const checkbox = document.getElementById('voice-debug-mode');
+    if (checkbox && data.debug_mode !== undefined) {
+      checkbox.checked = data.debug_mode;
+    }
+  } catch (error) {
+    console.error('Failed to load voice debug mode:', error);
+  }
+}
+
 // Handle Enter key in chat input
 function handleChatKeyPress(event) {
   if (event.ctrlKey && event.key === 'Enter') {
@@ -4603,7 +4729,198 @@ function readFileAsBase64(file) {
   });
 }
 
+// ============================================================================
+// Voice Call Management Functions
+// ============================================================================
+
+async function initiateVoiceCall() {
+  const userId = document.getElementById('voice-user-id').value.trim();
+  const channelId = document.getElementById('voice-channel-id').value.trim();
+  const debugMode = document.getElementById('voice-debug-mode').checked;
+  
+  // Validation
+  if (!userId) {
+    showNotification('Please enter a user ID', 'error');
+    return;
+  }
+  
+  if (!channelId) {
+    showNotification('Please enter a voice channel ID', 'error');
+    return;
+  }
+  
+  // Check if user IDs are valid (numeric)
+  if (isNaN(userId) || isNaN(channelId)) {
+    showNotification('User ID and Channel ID must be numeric', 'error');
+    return;
+  }
+  
+  // Set debug mode
+  try {
+    const debugFormData = new FormData();
+    debugFormData.append('enabled', debugMode);
+    await fetch('/voice/debug-mode', {
+      method: 'POST',
+      body: debugFormData
+    });
+  } catch (error) {
+    console.error('Failed to set debug mode:', error);
+  }
+  
+  // Disable button and show status
+  const callBtn = document.getElementById('voice-call-btn');
+  const cancelBtn = document.getElementById('voice-call-cancel-btn');
+  const statusDiv = document.getElementById('voice-call-status');
+  const statusText = document.getElementById('voice-call-status-text');
+  
+  callBtn.disabled = true;
+  statusDiv.style.display = 'block';
+  cancelBtn.style.display = 'inline-block';
+  voiceCallActive = true;
+  
+  try {
+    statusText.innerHTML = '⏳ Starting STT and TTS containers...';
+    
+    const formData = new FormData();
+    formData.append('user_id', userId);
+    formData.append('voice_channel_id', channelId);
+    
+    const response = await fetch('/voice/call', {
+      method: 'POST',
+      body: formData
+    });
+    
+    const data = await response.json();
+    
+    // Check for HTTP error status (422 validation error, etc.)
+    if (!response.ok) {
+      let errorMsg = data.error || data.detail || 'Unknown error';
+      // Handle FastAPI validation errors
+      if (data.detail && Array.isArray(data.detail)) {
+        errorMsg = data.detail.map(e => `${e.loc.join('.')}: ${e.msg}`).join(', ');
+      }
+      statusText.innerHTML = `❌ Error: ${errorMsg}`;
+      showNotification(`Voice call failed: ${errorMsg}`, 'error');
+      callBtn.disabled = false;
+      cancelBtn.style.display = 'none';
+      voiceCallActive = false;
+      return;
+    }
+    
+    if (!data.success) {
+      statusText.innerHTML = `❌ Error: ${data.error}`;
+      showNotification(`Voice call failed: ${data.error}`, 'error');
+      callBtn.disabled = false;
+      cancelBtn.style.display = 'none';
+      voiceCallActive = false;
+      return;
+    }
+    
+    // Success!
+    statusText.innerHTML = `✅ Voice call initiated!<br>User ID: ${data.user_id}<br>Channel: ${data.channel_id}`;
+    
+    // Show invite link
+    const inviteDiv = document.getElementById('voice-call-invite-link');
+    const inviteUrl = document.getElementById('voice-call-invite-url');
+    inviteUrl.href = data.invite_url;
+    inviteUrl.textContent = data.invite_url;
+    inviteDiv.style.display = 'block';
+    
+    // Add to call history
+    addVoiceCallToHistory(userId, channelId, data.invite_url);
+    
+    showNotification('Voice call initiated successfully!', 'success');
+    
+    // Auto-reset after 5 minutes (call should be done by then or timed out)
+    setTimeout(() => {
+      if (voiceCallActive) {
+        resetVoiceCall();
+      }
+    }, 300000); // 5 minutes
+    
+  } catch (error) {
+    console.error('Voice call error:', error);
+    statusText.innerHTML = `❌ Error: ${error.message}`;
+    showNotification(`Voice call error: ${error.message}`, 'error');
+    callBtn.disabled = false;
+    cancelBtn.style.display = 'none';
+    voiceCallActive = false;
+  }
+}
+
+function cancelVoiceCall() {
+  resetVoiceCall();
+  showNotification('Voice call cancelled', 'info');
+}
+
+function resetVoiceCall() {
+  const callBtn = document.getElementById('voice-call-btn');
+  const cancelBtn = document.getElementById('voice-call-cancel-btn');
+  const statusDiv = document.getElementById('voice-call-status');
+  
+  callBtn.disabled = false;
+  cancelBtn.style.display = 'none';
+  statusDiv.style.display = 'none';
+  voiceCallActive = false;
+  
+  // Clear inputs
+  document.getElementById('voice-user-id').value = '';
+  document.getElementById('voice-channel-id').value = '';
+}
+
+function addVoiceCallToHistory(userId, channelId, inviteUrl) {
+  const now = new Date();
+  const timestamp = now.toLocaleTimeString();
+  
+  const callEntry = {
+    userId: userId,
+    channelId: channelId,
+    inviteUrl: inviteUrl,
+    timestamp: timestamp
+  };
+  
+  voiceCallHistory.unshift(callEntry); // Add to front
+  
+  // Keep only last 10 calls
+  if (voiceCallHistory.length > 10) {
+    voiceCallHistory.pop();
+  }
+  
+  updateVoiceCallHistoryDisplay();
+}
+
+function updateVoiceCallHistoryDisplay() {
+  const historyDiv = document.getElementById('voice-call-history');
+  
+  if (voiceCallHistory.length === 0) {
+    historyDiv.innerHTML = '<div style="text-align: center; color: #888;">No calls yet. Start one above!</div>';
+    return;
+  }
+  
+  let html = '';
+  voiceCallHistory.forEach((call, index) => {
+    html += `
+      <div style="background: #242424; padding: 0.75rem; margin-bottom: 0.5rem; border-radius: 4px; border-left: 3px solid #61dafb;">
+        <div style="display: flex; justify-content: space-between; align-items: center;">
+          <div>
+            <strong>${call.timestamp}</strong>
+            <div style="font-size: 0.85rem; color: #aaa; margin-top: 0.3rem;">
+              User: <code>${call.userId}</code> | Channel: <code>${call.channelId}</code>
+            </div>
+          </div>
+          <a href="${call.inviteUrl}" target="_blank" style="color: #61dafb; text-decoration: none; padding: 0.3rem 0.7rem; background: #333; border-radius: 4px; font-size: 0.85rem;">
+            View Link →
+          </a>
+        </div>
+      </div>
+    `;
+  });
+  
+  historyDiv.innerHTML = html;
+}
+
 </script>
 
 </body>
 </html>
+

bot/utils/container_manager.py

@@ -0,0 +1,205 @@
+# container_manager.py
+"""
+Manages Docker containers for STT and TTS services.
+Handles startup, shutdown, and warmup detection.
+"""
+
+import asyncio
+import subprocess
+import aiohttp
+from utils.logger import get_logger
+
+logger = get_logger('container_manager')
+
+class ContainerManager:
+    """Manages STT and TTS Docker containers."""
+    
+    # Container names from docker-compose.yml
+    STT_CONTAINER = "miku-stt"
+    TTS_CONTAINER = "miku-rvc-api"
+    
+    # Warmup check endpoints
+    STT_HEALTH_URL = "http://miku-stt:8767/health"  # HTTP health check endpoint
+    TTS_HEALTH_URL = "http://miku-rvc-api:8765/health"
+    
+    # Warmup timeouts
+    STT_WARMUP_TIMEOUT = 30  # seconds
+    TTS_WARMUP_TIMEOUT = 60  # seconds (RVC takes longer)
+    
+    @classmethod
+    async def start_voice_containers(cls) -> bool:
+        """
+        Start STT and TTS containers and wait for them to warm up.
+        
+        Returns:
+            bool: True if both containers started and warmed up successfully
+        """
+        logger.info("🚀 Starting voice chat containers...")
+        
+        try:
+            # Start STT container using docker start (assumes container exists)
+            logger.info(f"Starting {cls.STT_CONTAINER}...")
+            result = subprocess.run(
+                ["docker", "start", cls.STT_CONTAINER],
+                capture_output=True,
+                text=True
+            )
+            
+            if result.returncode != 0:
+                logger.error(f"Failed to start {cls.STT_CONTAINER}: {result.stderr}")
+                return False
+            
+            logger.info(f"✓ {cls.STT_CONTAINER} started")
+            
+            # Start TTS container
+            logger.info(f"Starting {cls.TTS_CONTAINER}...")
+            result = subprocess.run(
+                ["docker", "start", cls.TTS_CONTAINER],
+                capture_output=True,
+                text=True
+            )
+            
+            if result.returncode != 0:
+                logger.error(f"Failed to start {cls.TTS_CONTAINER}: {result.stderr}")
+                return False
+            
+            logger.info(f"✓ {cls.TTS_CONTAINER} started")
+            
+            # Wait for warmup
+            logger.info("⏳ Waiting for containers to warm up...")
+            
+            stt_ready = await cls._wait_for_stt_warmup()
+            if not stt_ready:
+                logger.error("STT failed to warm up")
+                return False
+            
+            tts_ready = await cls._wait_for_tts_warmup()
+            if not tts_ready:
+                logger.error("TTS failed to warm up")
+                return False
+            
+            logger.info("✅ All voice containers ready!")
+            return True
+            
+        except Exception as e:
+            logger.error(f"Error starting voice containers: {e}")
+            return False
+    
+    @classmethod
+    async def stop_voice_containers(cls) -> bool:
+        """
+        Stop STT and TTS containers.
+        
+        Returns:
+            bool: True if containers stopped successfully
+        """
+        logger.info("🛑 Stopping voice chat containers...")
+        
+        try:
+            # Stop both containers
+            result = subprocess.run(
+                ["docker", "stop", cls.STT_CONTAINER, cls.TTS_CONTAINER],
+                capture_output=True,
+                text=True
+            )
+            
+            if result.returncode != 0:
+                logger.error(f"Failed to stop containers: {result.stderr}")
+                return False
+            
+            logger.info("✓ Voice containers stopped")
+            return True
+            
+        except Exception as e:
+            logger.error(f"Error stopping voice containers: {e}")
+            return False
+    
+    @classmethod
+    async def _wait_for_stt_warmup(cls) -> bool:
+        """
+        Wait for STT container to be ready by checking health endpoint.
+        
+        Returns:
+            bool: True if STT is ready within timeout
+        """
+        start_time = asyncio.get_event_loop().time()
+        
+        async with aiohttp.ClientSession() as session:
+            while (asyncio.get_event_loop().time() - start_time) < cls.STT_WARMUP_TIMEOUT:
+                try:
+                    async with session.get(cls.STT_HEALTH_URL, timeout=aiohttp.ClientTimeout(total=2)) as resp:
+                        if resp.status == 200:
+                            data = await resp.json()
+                            if data.get("status") == "ready" and data.get("warmed_up"):
+                                logger.info("✓ STT is ready")
+                                return True
+                except Exception:
+                    # Not ready yet, wait and retry
+                    pass
+                
+                await asyncio.sleep(2)
+        
+        logger.error(f"STT warmup timeout ({cls.STT_WARMUP_TIMEOUT}s)")
+        return False
+    
+    @classmethod
+    async def _wait_for_tts_warmup(cls) -> bool:
+        """
+        Wait for TTS container to be ready by checking health endpoint.
+        
+        Returns:
+            bool: True if TTS is ready within timeout
+        """
+        start_time = asyncio.get_event_loop().time()
+        
+        async with aiohttp.ClientSession() as session:
+            while (asyncio.get_event_loop().time() - start_time) < cls.TTS_WARMUP_TIMEOUT:
+                try:
+                    async with session.get(cls.TTS_HEALTH_URL, timeout=aiohttp.ClientTimeout(total=2)) as resp:
+                        if resp.status == 200:
+                            data = await resp.json()
+                            # RVC API returns "status": "healthy", not "ready"
+                            status_ok = data.get("status") in ["ready", "healthy"]
+                            if status_ok and data.get("warmed_up"):
+                                logger.info("✓ TTS is ready")
+                                return True
+                except Exception:
+                    # Not ready yet, wait and retry
+                    pass
+                
+                await asyncio.sleep(2)
+        
+        logger.error(f"TTS warmup timeout ({cls.TTS_WARMUP_TIMEOUT}s)")
+        return False
+        return False
+    
+    @classmethod
+    async def are_containers_running(cls) -> tuple[bool, bool]:
+        """
+        Check if STT and TTS containers are currently running.
+        
+        Returns:
+            tuple[bool, bool]: (stt_running, tts_running)
+        """
+        try:
+            # Check STT
+            result = subprocess.run(
+                ["docker", "inspect", "-f", "{{.State.Running}}", cls.STT_CONTAINER],
+                capture_output=True,
+                text=True
+            )
+            stt_running = result.returncode == 0 and result.stdout.strip() == "true"
+            
+            # Check TTS
+            result = subprocess.run(
+                ["docker", "inspect", "-f", "{{.State.Running}}", cls.TTS_CONTAINER],
+                capture_output=True,
+                text=True
+            )
+            tts_running = result.returncode == 0 and result.stdout.strip() == "true"
+            
+            return (stt_running, tts_running)
+            
+        except Exception as e:
+            logger.error(f"Error checking container status: {e}")
+            return (False, False)

bot/utils/logger.py

@@ -62,6 +62,7 @@ COMPONENTS = {
     'voice_manager': 'Voice channel session management',
     'voice_commands': 'Voice channel commands',
     'voice_audio': 'Voice audio streaming and TTS',
+    'container_manager': 'Docker container lifecycle management',
     'error_handler': 'Error detection and webhook notifications',
 }
 

bot/utils/stt_client.py

@@ -1,11 +1,15 @@
 """
-STT Client for Discord Bot
+STT Client for Discord Bot (RealtimeSTT Version)
 
-WebSocket client that connects to the STT server and handles:
+WebSocket client that connects to the RealtimeSTT server and handles:
 - Audio streaming to STT
-- Receiving VAD events
 - Receiving partial/final transcripts
-- Interruption detection
+
+Protocol:
+- Client sends: binary audio data (16kHz, 16-bit mono PCM)
+- Client sends: JSON {"command": "reset"} to reset state
+- Server sends: JSON {"type": "partial", "text": "...", "timestamp": float}
+- Server sends: JSON {"type": "final", "text": "...", "timestamp": float}
 """
 
 import aiohttp
@@ -19,7 +23,7 @@ logger = logging.getLogger('stt_client')
 
 class STTClient:
     """
-    WebSocket client for STT server communication.
+    WebSocket client for RealtimeSTT server communication.
     
     Handles audio streaming and receives transcription events.
     """
@@ -27,34 +31,28 @@ class STTClient:
     def __init__(
         self,
         user_id: str,
-        stt_url: str = "ws://miku-stt:8766/ws/stt",
-        on_vad_event: Optional[Callable] = None,
+        stt_url: str = "ws://miku-stt:8766",
         on_partial_transcript: Optional[Callable] = None,
         on_final_transcript: Optional[Callable] = None,
-        on_interruption: Optional[Callable] = None
     ):
         """
         Initialize STT client.
         
         Args:
-            user_id: Discord user ID
-            stt_url: Base WebSocket URL for STT server
-            on_vad_event: Callback for VAD events (event_dict)
+            user_id: Discord user ID (for logging purposes)
+            stt_url: WebSocket URL for STT server
             on_partial_transcript: Callback for partial transcripts (text, timestamp)
             on_final_transcript: Callback for final transcripts (text, timestamp)
-            on_interruption: Callback for interruption detection (probability)
         """
         self.user_id = user_id
-        self.stt_url = f"{stt_url}/{user_id}"
+        self.stt_url = stt_url
         
         # Callbacks
-        self.on_vad_event = on_vad_event
         self.on_partial_transcript = on_partial_transcript
         self.on_final_transcript = on_final_transcript
-        self.on_interruption = on_interruption
         
         # Connection state
-        self.websocket: Optional[aiohttp.ClientWebSocket] = None
+        self.websocket: Optional[aiohttp.ClientWebSocketResponse] = None
         self.session: Optional[aiohttp.ClientSession] = None
         self.connected = False
         self.running = False
@@ -65,7 +63,7 @@ class STTClient:
         logger.info(f"STT client initialized for user {user_id}")
     
     async def connect(self):
-        """Connect to STT WebSocket server."""
+        """Connect to RealtimeSTT WebSocket server."""
         if self.connected:
             logger.warning(f"Already connected for user {self.user_id}")
             return
@@ -74,202 +72,156 @@ class STTClient:
             self.session = aiohttp.ClientSession()
             self.websocket = await self.session.ws_connect(
                 self.stt_url,
-                heartbeat=30
+                heartbeat=30,
+                receive_timeout=60
             )
-            
-            # Wait for ready message
-            ready_msg = await self.websocket.receive_json()
-            logger.info(f"STT connected for user {self.user_id}: {ready_msg}")
-            
             self.connected = True
             self.running = True
             
-            # Start receive task
-            self._receive_task = asyncio.create_task(self._receive_events())
+            # Start background task to receive messages
+            self._receive_task = asyncio.create_task(self._receive_loop())
             
-            logger.info(f"✓ STT WebSocket connected for user {self.user_id}")
-        
+            logger.info(f"Connected to STT server at {self.stt_url} for user {self.user_id}")
         except Exception as e:
-            logger.error(f"Failed to connect STT for user {self.user_id}: {e}", exc_info=True)
-            await self.disconnect()
+            logger.error(f"Failed to connect to STT server: {e}")
+            await self._cleanup()
             raise
     
     async def disconnect(self):
-        """Disconnect from STT WebSocket."""
-        logger.info(f"Disconnecting STT for user {self.user_id}")
-        
+        """Disconnect from STT server."""
         self.running = False
-        self.connected = False
         
-        # Cancel receive task
-        if self._receive_task and not self._receive_task.done():
+        if self._receive_task:
             self._receive_task.cancel()
             try:
                 await self._receive_task
             except asyncio.CancelledError:
                 pass
+            self._receive_task = None
         
-        # Close WebSocket
+        await self._cleanup()
+        logger.info(f"Disconnected from STT server for user {self.user_id}")
+    
+    async def _cleanup(self):
+        """Clean up WebSocket and session."""
         if self.websocket:
-            await self.websocket.close()
+            try:
+                await self.websocket.close()
+            except Exception:
+                pass
             self.websocket = None
         
-        # Close session
         if self.session:
-            await self.session.close()
+            try:
+                await self.session.close()
+            except Exception:
+                pass
             self.session = None
         
-        logger.info(f"✓ STT disconnected for user {self.user_id}")
+        self.connected = False
     
     async def send_audio(self, audio_data: bytes):
         """
-        Send audio chunk to STT server.
+        Send raw audio data to STT server.
         
         Args:
-            audio_data: PCM audio (int16, 16kHz mono)
+            audio_data: Raw PCM audio (16kHz, 16-bit mono, little-endian)
         """
         if not self.connected or not self.websocket:
-            logger.warning(f"Cannot send audio, not connected for user {self.user_id}")
             return
         
         try:
             await self.websocket.send_bytes(audio_data)
-            logger.debug(f"Sent {len(audio_data)} bytes to STT")
-        
         except Exception as e:
-            logger.error(f"Failed to send audio to STT: {e}")
-            self.connected = False
+            logger.error(f"Failed to send audio: {e}")
+            await self._cleanup()
     
-    async def send_final(self):
-        """
-        Request final transcription from STT server.
-        
-        Call this when the user stops speaking to get the final transcript.
-        """
+    async def reset(self):
+        """Reset STT state (clear any pending transcription)."""
         if not self.connected or not self.websocket:
-            logger.warning(f"Cannot send final command, not connected for user {self.user_id}")
             return
         
         try:
-            command = json.dumps({"type": "final"})
-            await self.websocket.send_str(command)
-            logger.debug(f"Sent final command to STT")
-        
+            await self.websocket.send_json({"command": "reset"})
+            logger.debug(f"Sent reset command for user {self.user_id}")
         except Exception as e:
-            logger.error(f"Failed to send final command to STT: {e}")
-            self.connected = False
+            logger.error(f"Failed to send reset: {e}")
     
-    async def send_reset(self):
-        """
-        Reset the STT server's audio buffer.
-        
-        Call this to clear any buffered audio.
-        """
-        if not self.connected or not self.websocket:
-            logger.warning(f"Cannot send reset command, not connected for user {self.user_id}")
-            return
-        
-        try:
-            command = json.dumps({"type": "reset"})
-            await self.websocket.send_str(command)
-            logger.debug(f"Sent reset command to STT")
-        
-        except Exception as e:
-            logger.error(f"Failed to send reset command to STT: {e}")
-            self.connected = False
+    def is_connected(self) -> bool:
+        """Check if connected to STT server."""
+        return self.connected and self.websocket is not None
     
-    async def _receive_events(self):
-        """Background task to receive events from STT server."""
+    async def _receive_loop(self):
+        """Background task to receive messages from STT server."""
         try:
             while self.running and self.websocket:
                 try:
-                    msg = await self.websocket.receive()
+                    msg = await asyncio.wait_for(
+                        self.websocket.receive(),
+                        timeout=5.0
+                    )
                     
                     if msg.type == aiohttp.WSMsgType.TEXT:
-                        event = json.loads(msg.data)
-                        await self._handle_event(event)
-                    
+                        await self._handle_message(msg.data)
                     elif msg.type == aiohttp.WSMsgType.CLOSED:
-                        logger.info(f"STT WebSocket closed for user {self.user_id}")
+                        logger.warning(f"STT WebSocket closed for user {self.user_id}")
                         break
-                    
                     elif msg.type == aiohttp.WSMsgType.ERROR:
                         logger.error(f"STT WebSocket error for user {self.user_id}")
                         break
-                
-                except asyncio.CancelledError:
-                    break
-                except Exception as e:
-                    logger.error(f"Error receiving STT event: {e}", exc_info=True)
-        
+                        
+                except asyncio.TimeoutError:
+                    # Timeout is fine, just continue
+                    continue
+                    
+        except asyncio.CancelledError:
+            pass
+        except Exception as e:
+            logger.error(f"Error in STT receive loop: {e}")
         finally:
             self.connected = False
-            logger.info(f"STT receive task ended for user {self.user_id}")
     
-    async def _handle_event(self, event: dict):
-        """
-        Handle incoming STT event.
-        
-        Args:
-            event: Event dictionary from STT server
-        """
-        event_type = event.get('type')
-        
-        if event_type == 'transcript':
-            # New ONNX server protocol: single transcript type with is_final flag
-            text = event.get('text', '')
-            is_final = event.get('is_final', False)
-            timestamp = event.get('timestamp', 0)
+    async def _handle_message(self, data: str):
+        """Handle a message from the STT server."""
+        try:
+            message = json.loads(data)
+            msg_type = message.get("type")
+            text = message.get("text", "")
+            timestamp = message.get("timestamp", 0)
             
-            if is_final:
-                logger.info(f"Final transcript [{self.user_id}]: {text}")
-                if self.on_final_transcript:
-                    await self.on_final_transcript(text, timestamp)
-            else:
-                logger.info(f"Partial transcript [{self.user_id}]: {text}")
-                if self.on_partial_transcript:
-                    await self.on_partial_transcript(text, timestamp)
-        
-        elif event_type == 'vad':
-            # VAD event: speech detection (legacy support)
-            logger.debug(f"VAD event: {event}")
-            if self.on_vad_event:
-                await self.on_vad_event(event)
-        
-        elif event_type == 'partial':
-            # Legacy protocol support: partial transcript
-            text = event.get('text', '')
-            timestamp = event.get('timestamp', 0)
-            logger.info(f"Partial transcript [{self.user_id}]: {text}")
-            if self.on_partial_transcript:
-                await self.on_partial_transcript(text, timestamp)
-        
-        elif event_type == 'final':
-            # Legacy protocol support: final transcript
-            text = event.get('text', '')
-            timestamp = event.get('timestamp', 0)
-            logger.info(f"Final transcript [{self.user_id}]: {text}")
-            if self.on_final_transcript:
-                await self.on_final_transcript(text, timestamp)
-        
-        elif event_type == 'interruption':
-            # Interruption detected (legacy support)
-            probability = event.get('probability', 0)
-            logger.info(f"Interruption detected from user {self.user_id} (prob={probability:.3f})")
-            if self.on_interruption:
-                await self.on_interruption(probability)
-        
-        elif event_type == 'info':
-            # Info message
-            logger.info(f"STT info: {event.get('message', '')}")
-        
-        elif event_type == 'error':
-            # Error message
-            logger.error(f"STT error: {event.get('message', '')}")
-        
-        else:
-            logger.warning(f"Unknown STT event type: {event_type}")
+            if msg_type == "partial":
+                if self.on_partial_transcript and text:
+                    await self._call_callback(
+                        self.on_partial_transcript, 
+                        text, 
+                        timestamp
+                    )
+                    
+            elif msg_type == "final":
+                if self.on_final_transcript and text:
+                    await self._call_callback(
+                        self.on_final_transcript,
+                        text,
+                        timestamp
+                    )
+            
+            elif msg_type == "connected":
+                logger.info(f"STT server confirmed connection for user {self.user_id}")
+                
+            elif msg_type == "error":
+                error_msg = message.get("error", "Unknown error")
+                logger.error(f"STT server error: {error_msg}")
+                
+        except json.JSONDecodeError:
+            logger.warning(f"Invalid JSON from STT server: {data[:100]}")
+        except Exception as e:
+            logger.error(f"Error handling STT message: {e}")
     
-    def is_connected(self) -> bool:
-        """Check if STT client is connected."""
-        return self.connected
+    async def _call_callback(self, callback, *args):
+        """Safely call a callback, handling both sync and async functions."""
+        try:
+            result = callback(*args)
+            if asyncio.iscoroutine(result):
+                await result
+        except Exception as e:
+            logger.error(f"Error in STT callback: {e}")

bot/utils/voice_audio.py

@@ -6,6 +6,7 @@ Uses aiohttp for WebSocket communication (compatible with FastAPI).
 
 import asyncio
 import json
+import re
 import numpy as np
 from typing import Optional
 import discord
@@ -29,6 +30,25 @@ CHANNELS = 2  # Stereo for Discord
 FRAME_LENGTH = 0.02  # 20ms frames
 SAMPLES_PER_FRAME = int(SAMPLE_RATE * FRAME_LENGTH)  # 960 samples
 
+# Emoji pattern for filtering
+# Covers most emoji ranges including emoticons, symbols, pictographs, etc.
+EMOJI_PATTERN = re.compile(
+    "["
+    "\U0001F600-\U0001F64F"  # emoticons
+    "\U0001F300-\U0001F5FF"  # symbols & pictographs
+    "\U0001F680-\U0001F6FF"  # transport & map symbols
+    "\U0001F1E0-\U0001F1FF"  # flags (iOS)
+    "\U00002702-\U000027B0"  # dingbats
+    "\U000024C2-\U0001F251"  # enclosed characters
+    "\U0001F900-\U0001F9FF"  # supplemental symbols and pictographs
+    "\U0001FA00-\U0001FA6F"  # chess symbols
+    "\U0001FA70-\U0001FAFF"  # symbols and pictographs extended-A
+    "\U00002600-\U000026FF"  # miscellaneous symbols
+    "\U00002700-\U000027BF"  # dingbats
+    "]+",
+    flags=re.UNICODE
+)
+
 
 class MikuVoiceSource(discord.AudioSource):
     """
@@ -38,8 +58,9 @@ class MikuVoiceSource(discord.AudioSource):
     """
     
     def __init__(self):
-        self.websocket_url = "ws://172.25.0.1:8765/ws/stream"
-        self.health_url = "http://172.25.0.1:8765/health"
+        # Use Docker hostname for RVC service (miku-rvc-api is on miku-voice-network)
+        self.websocket_url = "ws://miku-rvc-api:8765/ws/stream"
+        self.health_url = "http://miku-rvc-api:8765/health"
         self.session = None
         self.websocket = None
         self.audio_buffer = bytearray()
@@ -230,11 +251,26 @@ class MikuVoiceSource(discord.AudioSource):
         """
         Send a text token to TTS for voice generation.
         Queues tokens if pipeline is still warming up or connection failed.
+        Filters out emojis to prevent TTS hallucinations.
         
         Args:
             token: Text token to synthesize
             pitch_shift: Pitch adjustment (-12 to +12 semitones)
         """
+        # Filter out emojis from the token (preserve whitespace!)
+        original_token = token
+        token = EMOJI_PATTERN.sub('', token)
+        
+        # If token is now empty or only whitespace after emoji removal, skip it
+        if not token or not token.strip():
+            if original_token != token:
+                logger.debug(f"Skipped token (only emojis): '{original_token}'")
+            return
+        
+        # Log if we filtered out emojis
+        if original_token != token:
+            logger.debug(f"Filtered emojis from token: '{original_token}' -> '{token}'")
+        
         # If not warmed up yet or no connection, queue the token
         if not self.warmed_up or not self.websocket:
             self.token_queue.append((token, pitch_shift))

bot/utils/voice_manager.py

@@ -398,6 +398,13 @@ class VoiceSession:
         # Voice chat conversation history (last 8 exchanges)
         self.conversation_history = []  # List of {"role": "user"/"assistant", "content": str}
         
+        # Voice call management (for automated calls from web UI)
+        self.call_user_id: Optional[int] = None  # User ID that was called
+        self.call_timeout_task: Optional[asyncio.Task] = None  # 30min timeout task
+        self.user_has_joined = False  # Track if user joined the call
+        self.auto_leave_task: Optional[asyncio.Task] = None  # 45s auto-leave task
+        self.user_leave_time: Optional[float] = None  # When user left the channel
+        
         logger.info(f"VoiceSession created for {voice_channel.name} in guild {guild_id}")
     
     async def start_audio_streaming(self):
@@ -488,6 +495,57 @@ class VoiceSession:
             self.voice_receiver = None
             logger.info("✓ Stopped all listening")
     
+    async def on_user_join(self, user_id: int):
+        """Called when a user joins the voice channel."""
+        # If this is a voice call and the expected user joined
+        if self.call_user_id and user_id == self.call_user_id:
+            self.user_has_joined = True
+            logger.info(f"✓ Call user {user_id} joined the channel")
+            
+            # Cancel timeout task since user joined
+            if self.call_timeout_task:
+                self.call_timeout_task.cancel()
+                self.call_timeout_task = None
+            
+            # Cancel auto-leave task if it was running
+            if self.auto_leave_task:
+                self.auto_leave_task.cancel()
+                self.auto_leave_task = None
+                self.user_leave_time = None
+    
+    async def on_user_leave(self, user_id: int):
+        """Called when a user leaves the voice channel."""
+        # If this is the call user leaving
+        if self.call_user_id and user_id == self.call_user_id and self.user_has_joined:
+            import time
+            self.user_leave_time = time.time()
+            logger.info(f"📴 Call user {user_id} left - starting 45s auto-leave timer")
+            
+            # Start 45s auto-leave timer
+            self.auto_leave_task = asyncio.create_task(self._auto_leave_after_user_disconnect())
+    
+    async def _auto_leave_after_user_disconnect(self):
+        """Auto-leave 45s after user disconnects."""
+        try:
+            await asyncio.sleep(45)
+            
+            logger.info("⏰ 45s timeout reached - auto-leaving voice channel")
+            
+            # End the session (will trigger cleanup)
+            from utils.voice_manager import VoiceSessionManager
+            session_manager = VoiceSessionManager()
+            await session_manager.end_session()
+            
+            # Stop containers
+            from utils.container_manager import ContainerManager
+            await ContainerManager.stop_voice_containers()
+            
+            logger.info("✓ Auto-leave complete")
+            
+        except asyncio.CancelledError:
+            # User rejoined, normal operation
+            logger.info("Auto-leave cancelled - user rejoined")
+    
     async def on_user_vad_event(self, user_id: int, event: dict):
         """Called when VAD detects speech state change."""
         event_type = event.get('event')
@@ -515,7 +573,10 @@ class VoiceSession:
             # Get user info for notification
             user = self.voice_channel.guild.get_member(user_id)
             user_name = user.name if user else f"User {user_id}"
-            await self.text_channel.send(f"💬 *{user_name} said: \"{text}\" (interrupted but too brief - talk longer to interrupt)*")
+            
+            # Only send message if debug mode is on
+            if globals.VOICE_DEBUG_MODE:
+                await self.text_channel.send(f"💬 *{user_name} said: \"{text}\" (interrupted but too brief - talk longer to interrupt)*")
             return
         
         logger.info(f"✓ Processing final transcript (miku_speaking={self.miku_speaking})")
@@ -530,12 +591,14 @@ class VoiceSession:
         stop_phrases = ["stop talking", "be quiet", "shut up", "stop speaking", "silence"]
         if any(phrase in text.lower() for phrase in stop_phrases):
             logger.info(f"🤫 Stop command detected: {text}")
-            await self.text_channel.send(f"🎤 {user.name}: *\"{text}\"*")
-            await self.text_channel.send(f"🤫 *Miku goes quiet*")
+            if globals.VOICE_DEBUG_MODE:
+                await self.text_channel.send(f"🎤 {user.name}: *\"{text}\"*")
+                await self.text_channel.send(f"🤫 *Miku goes quiet*")
             return
         
-        # Show what user said
-        await self.text_channel.send(f"🎤 {user.name}: *\"{text}\"*")
+        # Show what user said (only in debug mode)
+        if globals.VOICE_DEBUG_MODE:
+            await self.text_channel.send(f"🎤 {user.name}: *\"{text}\"*")
         
         # Generate LLM response and speak it
         await self._generate_voice_response(user, text)
@@ -582,14 +645,15 @@ class VoiceSession:
         logger.info(f"⏸️ Pausing for {self.interruption_silence_duration}s after interruption")
         await asyncio.sleep(self.interruption_silence_duration)
         
-        # 5. Add interruption marker to conversation history
+        # Add interruption marker to conversation history
         self.conversation_history.append({
             "role": "assistant",
             "content": "[INTERRUPTED - user started speaking]"
         })
         
-        # Show interruption in chat
-        await self.text_channel.send(f"⚠️ *{user_name} interrupted Miku*")
+        # Show interruption in chat (only in debug mode)
+        if globals.VOICE_DEBUG_MODE:
+            await self.text_channel.send(f"⚠️ *{user_name} interrupted Miku*")
         
         logger.info(f"✓ Interruption handled, ready for next input")
     
@@ -599,8 +663,10 @@ class VoiceSession:
         Called when VAD-based interruption detection is used.
         """
         await self.on_user_interruption(user_id)
-        user = self.voice_channel.guild.get_member(user_id)
-        await self.text_channel.send(f"⚠️ *{user.name if user else 'User'} interrupted Miku*")
+        # Only show interruption message in debug mode
+        if globals.VOICE_DEBUG_MODE:
+            user = self.voice_channel.guild.get_member(user_id)
+            await self.text_channel.send(f"⚠️ *{user.name if user else 'User'} interrupted Miku*")
     
     async def _generate_voice_response(self, user: discord.User, text: str):
         """
@@ -624,13 +690,13 @@ class VoiceSession:
             self.miku_speaking = True
             logger.info(f"   → miku_speaking is now: {self.miku_speaking}")
             
-            # Show processing
-            await self.text_channel.send(f"💭 *Miku is thinking...*")
+            # Show processing (only in debug mode)
+            if globals.VOICE_DEBUG_MODE:
+                await self.text_channel.send(f"💭 *Miku is thinking...*")
             
             # Import here to avoid circular imports
             from utils.llm import get_current_gpu_url
             import aiohttp
-            import globals
             
             # Load personality and lore
             miku_lore = ""
@@ -657,8 +723,11 @@ VOICE CHAT CONTEXT:
   * Stories/explanations: 4-6 sentences when asked for details
 - Match the user's energy and conversation style
 - IMPORTANT: Only respond in ENGLISH! The TTS system cannot handle Japanese or other languages well.
+- IMPORTANT: Do not include emojis in your response! The TTS system cannot handle them well.
+- IMPORTANT: Do NOT prefix your response with your name (like "Miku:" or "Hatsune Miku:")! Just speak naturally - you're already known to be speaking.
 - Be expressive and use casual language, but stay in character as Miku
 - If user says "stop talking" or "be quiet", acknowledge briefly and stop
+- NOTE: You will automatically disconnect 45 seconds after {user.name} leaves the voice channel, so you can mention this if asked about leaving
 
 Remember: This is a live voice conversation - be natural, not formulaic!"""
 
@@ -742,15 +811,19 @@ Remember: This is a live voice conversation - be natural, not formulaic!"""
             if self.miku_speaking:
                 await self.audio_source.flush()
                 
-                # Add Miku's complete response to history
+                # Filter out self-referential prefixes from response
+                filtered_response = self._filter_name_prefixes(full_response.strip())
+                
+                # Add Miku's complete response to history (use filtered version)
                 self.conversation_history.append({
                     "role": "assistant",
-                    "content": full_response.strip()
+                    "content": filtered_response
                 })
                 
-                # Show response
-                await self.text_channel.send(f"🎤 Miku: *\"{full_response.strip()}\"*")
-                logger.info(f"✓ Voice response complete: {full_response.strip()}")
+                # Show response (only in debug mode)
+                if globals.VOICE_DEBUG_MODE:
+                    await self.text_channel.send(f"🎤 Miku: *\"{filtered_response}\"*")
+                logger.info(f"✓ Voice response complete: {filtered_response}")
             else:
                 # Interrupted - don't add incomplete response to history
                 # (interruption marker already added by on_user_interruption)
@@ -763,6 +836,35 @@ Remember: This is a live voice conversation - be natural, not formulaic!"""
         finally:
             self.miku_speaking = False
     
+    def _filter_name_prefixes(self, text: str) -> str:
+        """
+        Filter out self-referential name prefixes from Miku's responses.
+        
+        Removes patterns like:
+        - "Miku: rest of text"
+        - "Hatsune Miku: rest of text"
+        - "miku: rest of text" (case insensitive)
+        
+        Args:
+            text: Raw response text
+            
+        Returns:
+            Filtered text without name prefixes
+        """
+        import re
+        
+        # Pattern matches "Miku:" or "Hatsune Miku:" at the start of the text (case insensitive)
+        # Captures any amount of whitespace after the colon
+        pattern = r'^(?:Hatsune\s+)?Miku:\s*'
+        
+        filtered = re.sub(pattern, '', text, flags=re.IGNORECASE)
+        
+        # Log if we filtered something
+        if filtered != text:
+            logger.info(f"Filtered name prefix: '{text[:30]}...' -> '{filtered[:30]}...'")
+        
+        return filtered
+    
     async def _cancel_tts(self):
         """
         Immediately cancel TTS synthesis and clear all audio buffers.

bot/utils/voice_receiver.py

@@ -8,6 +8,8 @@ Uses the discord-ext-voice-recv extension for proper audio receiving support.
 import asyncio
 import audioop
 import logging
+import struct
+import array
 from typing import Dict, Optional
 from collections import deque
 
@@ -27,13 +29,13 @@ class VoiceReceiverSink(voice_recv.AudioSink):
     decodes/resamples as needed, and sends to STT clients for transcription.
     """
     
-    def __init__(self, voice_manager, stt_url: str = "ws://miku-stt:8766/ws/stt"):
+    def __init__(self, voice_manager, stt_url: str = "ws://miku-stt:8766"):
         """
         Initialize Voice Receiver.
         
         Args:
             voice_manager: The voice manager instance
-            stt_url: Base URL for STT WebSocket server with path (port 8766 inside container)
+            stt_url: WebSocket URL for RealtimeSTT server (port 8766 inside container)
         """
         super().__init__()
         self.voice_manager = voice_manager
@@ -72,6 +74,68 @@ class VoiceReceiverSink(voice_recv.AudioSink):
         
         logger.info("VoiceReceiverSink initialized")
     
+    @staticmethod
+    def _preprocess_audio(pcm_data: bytes) -> bytes:
+        """
+        Preprocess audio for better STT accuracy.
+        
+        Applies:
+        1. DC offset removal
+        2. High-pass filter (80Hz) to remove rumble
+        3. RMS normalization
+        
+        Args:
+            pcm_data: Raw PCM audio (16-bit mono, 16kHz)
+            
+        Returns:
+            Preprocessed PCM audio
+        """
+        try:
+            # Convert bytes to array of int16 samples
+            samples = array.array('h', pcm_data)
+            
+            # 1. Remove DC offset (mean)
+            mean = sum(samples) / len(samples) if samples else 0
+            samples = array.array('h', [int(s - mean) for s in samples])
+            
+            # 2. Simple high-pass filter (80Hz @ 16kHz)
+            # Using a simple first-order HPF: y[n] = x[n] - x[n-1] + 0.95 * y[n-1]
+            alpha = 0.95  # Filter coefficient (roughly 80Hz cutoff at 16kHz)
+            filtered = array.array('h')
+            prev_input = 0
+            prev_output = 0
+            
+            for sample in samples:
+                output = sample - prev_input + alpha * prev_output
+                filtered.append(int(max(-32768, min(32767, output))))  # Clamp to int16 range
+                prev_input = sample
+                prev_output = output
+            
+            # 3. RMS normalization to target level
+            # Calculate RMS
+            sum_squares = sum(s * s for s in filtered)
+            rms = (sum_squares / len(filtered)) ** 0.5 if filtered else 1.0
+            
+            # Target RMS (roughly -20dB)
+            target_rms = 3276.8  # 10% of max int16 range
+            
+            # Normalize if RMS is too low or too high
+            if rms > 100:  # Only normalize if there's actual signal
+                gain = target_rms / rms
+                # Limit gain to prevent over-amplification of noise
+                gain = min(gain, 4.0)  # Max 12dB boost
+                normalized = array.array('h', [
+                    int(max(-32768, min(32767, s * gain))) for s in filtered
+                ])
+                return normalized.tobytes()
+            else:
+                # Signal too weak, return filtered without normalization
+                return filtered.tobytes()
+                
+        except Exception as e:
+            logger.debug(f"Audio preprocessing failed, using raw audio: {e}")
+            return pcm_data
+    
     def wants_opus(self) -> bool:
         """
         Tell discord-ext-voice-recv we want Opus data, NOT decoded PCM.
@@ -144,6 +208,10 @@ class VoiceReceiverSink(voice_recv.AudioSink):
             # Discord sends 20ms chunks: 960 samples @ 48kHz → 320 samples @ 16kHz
             pcm_16k, _ = audioop.ratecv(pcm_mono, 2, 1, 48000, 16000, None)
             
+            # Preprocess audio for better STT accuracy
+            # (DC offset removal, high-pass filter, RMS normalization)
+            pcm_16k = self._preprocess_audio(pcm_16k)
+            
             # Send to STT client (schedule on event loop thread-safely)
             asyncio.run_coroutine_threadsafe(
                 self._send_audio_chunk(user_id, pcm_16k),
@@ -184,21 +252,16 @@ class VoiceReceiverSink(voice_recv.AudioSink):
         self.audio_buffers[user_id] = deque(maxlen=1000)
         
         # Create STT client with callbacks
+        # RealtimeSTT handles VAD internally, so we only need partial/final callbacks
         stt_client = STTClient(
             user_id=user_id,
             stt_url=self.stt_url,
-            on_vad_event=lambda event: asyncio.create_task(
-                self._on_vad_event(user_id, event)
-            ),
             on_partial_transcript=lambda text, timestamp: asyncio.create_task(
                 self._on_partial_transcript(user_id, text)
             ),
             on_final_transcript=lambda text, timestamp: asyncio.create_task(
                 self._on_final_transcript(user_id, text, user)
             ),
-            on_interruption=lambda prob: asyncio.create_task(
-                self._on_interruption(user_id, prob)
-            )
         )
         
         # Connect to STT server
@@ -279,16 +342,16 @@ class VoiceReceiverSink(voice_recv.AudioSink):
         """
         Send audio chunk to STT client.
         
-        Buffers audio until we have 512 samples (32ms @ 16kHz) which is what
-        Silero VAD expects. Discord sends 320 samples (20ms), so we buffer
-        2 chunks and send 640 samples, then the STT server can split it.
+        RealtimeSTT expects 16kHz mono 16-bit PCM audio.
+        We buffer audio to send larger chunks for efficiency.
+        VAD and silence detection is handled by RealtimeSTT.
         
         Args:
             user_id: Discord user ID
-            audio_data: PCM audio (int16, 16kHz mono, 320 samples = 640 bytes)
+            audio_data: PCM audio (int16, 16kHz mono)
         """
         stt_client = self.stt_clients.get(user_id)
-        if not stt_client or not stt_client.is_connected():
+        if not stt_client or not stt_client.connected:
             return
         
         try:
@@ -299,11 +362,9 @@ class VoiceReceiverSink(voice_recv.AudioSink):
             buffer = self.audio_buffers[user_id]
             buffer.append(audio_data)
             
-            # Silero VAD expects 512 samples @ 16kHz (1024 bytes)
-            # Discord gives us 320 samples (640 bytes) every 20ms
-            # Buffer 2 chunks = 640 samples = 1280 bytes, send as one chunk
-            SAMPLES_NEEDED = 512  # What VAD wants
-            BYTES_NEEDED = SAMPLES_NEEDED * 2  # int16 = 2 bytes per sample
+            # Buffer and send in larger chunks for efficiency
+            # RealtimeSTT will handle VAD internally
+            BYTES_NEEDED = 1024  # 512 samples * 2 bytes
             
             # Check if we have enough buffered audio
             total_bytes = sum(len(chunk) for chunk in buffer)
@@ -313,16 +374,10 @@ class VoiceReceiverSink(voice_recv.AudioSink):
                 combined = b''.join(buffer)
                 buffer.clear()
                 
-                # Send in 512-sample (1024-byte) chunks
-                for i in range(0, len(combined), BYTES_NEEDED):
-                    chunk = combined[i:i+BYTES_NEEDED]
-                    if len(chunk) == BYTES_NEEDED:
-                        await stt_client.send_audio(chunk)
-                    else:
-                        # Put remaining partial chunk back in buffer
-                        buffer.append(chunk)
+                # Send all audio to STT (RealtimeSTT handles VAD internally)
+                await stt_client.send_audio(combined)
                 
-                # Track audio time for silence detection
+                # Track audio time for interruption detection
                 import time
                 current_time = time.time()
                 self.last_audio_time[user_id] = current_time
@@ -331,103 +386,57 @@ class VoiceReceiverSink(voice_recv.AudioSink):
                 # Check if Miku is speaking and user is interrupting
                 # Note: self.voice_manager IS the VoiceSession, not the VoiceManager singleton
                 miku_speaking = self.voice_manager.miku_speaking
-                logger.debug(f"[INTERRUPTION CHECK] user={user_id}, miku_speaking={miku_speaking}")
                 
                 if miku_speaking:
-                    # Track interruption
-                    if user_id not in self.interruption_start_time:
-                        # First chunk during Miku's speech
-                        self.interruption_start_time[user_id] = current_time
-                        self.interruption_audio_count[user_id] = 1
+                    # Calculate RMS to detect if user is actually speaking
+                    # (not just silence/background noise)
+                    rms = audioop.rms(combined, 2)
+                    RMS_THRESHOLD = 500  # Adjust threshold - higher = less sensitive
+                    
+                    if rms > RMS_THRESHOLD:
+                        # User is actually speaking - track as potential interruption
+                        if user_id not in self.interruption_start_time:
+                            # First chunk during Miku's speech with actual audio
+                            self.interruption_start_time[user_id] = current_time
+                            self.interruption_audio_count[user_id] = 1
+                            logger.debug(f"Potential interruption start (rms={rms})")
+                        else:
+                            # Increment chunk count
+                            self.interruption_audio_count[user_id] += 1
+                        
+                        # Calculate interruption duration
+                        interruption_duration = current_time - self.interruption_start_time[user_id]
+                        chunk_count = self.interruption_audio_count[user_id]
+                        
+                        # Check if interruption threshold is met
+                        if (interruption_duration >= self.interruption_threshold_time and 
+                            chunk_count >= self.interruption_threshold_chunks):
+                            
+                            # Trigger interruption!
+                            logger.info(f"🛑 User {user_id} interrupted Miku (duration={interruption_duration:.2f}s, chunks={chunk_count}, rms={rms})")
+                            logger.info(f"   → Stopping Miku's TTS and LLM, will process user's speech when finished")
+                            
+                            # Reset interruption tracking
+                            self.interruption_start_time.pop(user_id, None)
+                            self.interruption_audio_count.pop(user_id, None)
+                            
+                            # Call interruption handler (this sets miku_speaking=False)
+                            asyncio.create_task(
+                                self.voice_manager.on_user_interruption(user_id)
+                            )
                     else:
-                        # Increment chunk count
-                        self.interruption_audio_count[user_id] += 1
-                    
-                    # Calculate interruption duration
-                    interruption_duration = current_time - self.interruption_start_time[user_id]
-                    chunk_count = self.interruption_audio_count[user_id]
-                    
-                    # Check if interruption threshold is met
-                    if (interruption_duration >= self.interruption_threshold_time and 
-                        chunk_count >= self.interruption_threshold_chunks):
-                        
-                        # Trigger interruption!
-                        logger.info(f"🛑 User {user_id} interrupted Miku (duration={interruption_duration:.2f}s, chunks={chunk_count})")
-                        logger.info(f"   → Stopping Miku's TTS and LLM, will process user's speech when finished")
-                        
-                        # Reset interruption tracking
+                        # Audio below RMS threshold (silence) - reset interruption tracking
+                        # This ensures brief pauses in speech reset the counter
                         self.interruption_start_time.pop(user_id, None)
                         self.interruption_audio_count.pop(user_id, None)
-                        
-                        # Call interruption handler (this sets miku_speaking=False)
-                        asyncio.create_task(
-                            self.voice_manager.on_user_interruption(user_id)
-                        )
                 else:
                     # Miku not speaking, clear interruption tracking
                     self.interruption_start_time.pop(user_id, None)
                     self.interruption_audio_count.pop(user_id, None)
-                
-                # Cancel existing silence task if any
-                if user_id in self.silence_tasks and not self.silence_tasks[user_id].done():
-                    self.silence_tasks[user_id].cancel()
-                
-                # Start new silence detection task
-                self.silence_tasks[user_id] = asyncio.create_task(
-                    self._detect_silence(user_id)
-                )
                         
         except Exception as e:
             logger.error(f"Failed to send audio chunk for user {user_id}: {e}")
     
-    async def _detect_silence(self, user_id: int):
-        """
-        Wait for silence timeout and send 'final' command to STT.
-        
-        This is called after each audio chunk. If no more audio arrives within
-        the silence_timeout period, we send the 'final' command to get the
-        complete transcription.
-        
-        Args:
-            user_id: Discord user ID
-        """
-        try:
-            # Wait for silence timeout
-            await asyncio.sleep(self.silence_timeout)
-            
-            # Check if we still have an active STT client
-            stt_client = self.stt_clients.get(user_id)
-            if not stt_client or not stt_client.is_connected():
-                return
-            
-            # Send final command to get complete transcription
-            logger.debug(f"Silence detected for user {user_id}, requesting final transcript")
-            await stt_client.send_final()
-            
-        except asyncio.CancelledError:
-            # Task was cancelled because new audio arrived
-            pass
-        except Exception as e:
-            logger.error(f"Error in silence detection for user {user_id}: {e}")
-    
-    async def _on_vad_event(self, user_id: int, event: dict):
-        """
-        Handle VAD event from STT.
-        
-        Args:
-            user_id: Discord user ID
-            event: VAD event dictionary with 'event' and 'probability' keys
-        """
-        user = self.users.get(user_id)
-        event_type = event.get('event', 'unknown')
-        probability = event.get('probability', 0.0)
-        
-        logger.debug(f"VAD [{user.name if user else user_id}]: {event_type} (prob={probability:.3f})")
-        
-        # Notify voice manager - pass the full event dict
-        if hasattr(self.voice_manager, 'on_user_vad_event'):
-            await self.voice_manager.on_user_vad_event(user_id, event)
-    
     async def _on_partial_transcript(self, user_id: int, text: str):
         """
         Handle partial transcript from STT.
@@ -438,7 +447,6 @@ class VoiceReceiverSink(voice_recv.AudioSink):
         """
         user = self.users.get(user_id)
         logger.info(f"[VOICE_RECEIVER] Partial [{user.name if user else user_id}]: {text}")
-        print(f"[DEBUG] PARTIAL TRANSCRIPT RECEIVED: {text}")  # Extra debug
         
         # Notify voice manager
         if hasattr(self.voice_manager, 'on_partial_transcript'):
@@ -456,29 +464,11 @@ class VoiceReceiverSink(voice_recv.AudioSink):
             user: Discord user object
         """
         logger.info(f"[VOICE_RECEIVER] Final [{user.name if user else user_id}]: {text}")
-        print(f"[DEBUG] FINAL TRANSCRIPT RECEIVED: {text}")  # Extra debug
         
         # Notify voice manager - THIS TRIGGERS LLM RESPONSE
         if hasattr(self.voice_manager, 'on_final_transcript'):
             await self.voice_manager.on_final_transcript(user_id, text)
     
-    async def _on_interruption(self, user_id: int, probability: float):
-        """
-        Handle interruption detection from STT.
-        
-        This cancels Miku's current speech if user interrupts.
-        
-        Args:
-            user_id: Discord user ID
-            probability: Interruption confidence probability
-        """
-        user = self.users.get(user_id)
-        logger.info(f"Interruption from [{user.name if user else user_id}] (prob={probability:.3f})")
-        
-        # Notify voice manager - THIS CANCELS MIKU'S SPEECH
-        if hasattr(self.voice_manager, 'on_user_interruption'):
-            await self.voice_manager.on_user_interruption(user_id, probability)
-    
     def get_listening_users(self) -> list:
         """
         Get list of users currently being listened to.
@@ -489,30 +479,10 @@ class VoiceReceiverSink(voice_recv.AudioSink):
         return [
             {
                 'user_id': user_id,
-                'username': user.name if user else 'Unknown',
-                'connected': client.is_connected()
+                'username': self.users.get(user_id, {}).name if self.users.get(user_id) else 'Unknown',
+                'connected': self.stt_clients.get(user_id, {}).connected if self.stt_clients.get(user_id) else False
             }
-            for user_id, (user, client) in 
-            [(uid, (self.users.get(uid), self.stt_clients.get(uid))) 
-             for uid in self.stt_clients.keys()]
+            for user_id in self.stt_clients.keys()
         ]
     
-    @voice_recv.AudioSink.listener()
-    def on_voice_member_speaking_start(self, member: discord.Member):
-        """
-        Called when a member starts speaking (green circle appears).
-        
-        This is a virtual event from discord-ext-voice-recv based on packet activity.
-        """
-        if member.id in self.stt_clients:
-            logger.debug(f"🎤 {member.name} started speaking")
-    
-    @voice_recv.AudioSink.listener()
-    def on_voice_member_speaking_stop(self, member: discord.Member):
-        """
-        Called when a member stops speaking (green circle disappears).
-        
-        This is a virtual event from discord-ext-voice-recv based on packet activity.
-        """
-        if member.id in self.stt_clients:
-            logger.debug(f"🔇 {member.name} stopped speaking")
+    # Discord VAD events removed - we rely entirely on RealtimeSTT's VAD for speech detection