diff --git a/bot/requirements.txt b/bot/requirements.txt
index 512de89..d5fad8b 100644
--- a/bot/requirements.txt
+++ b/bot/requirements.txt
@@ -14,6 +14,7 @@ Pillow
 opencv-contrib-python
 numpy
 transformers
+scikit-learn
 PyNaCl>=1.5.0
 websockets>=12.0
 discord-ext-voice-recv
diff --git a/stt-realtime/Dockerfile b/stt-realtime/Dockerfile
index 7b64fc5..eba464b 100644
--- a/stt-realtime/Dockerfile
+++ b/stt-realtime/Dockerfile
@@ -1,8 +1,14 @@
 # RealtimeSTT Container
 # Uses Faster-Whisper with CUDA for GPU-accelerated inference
 # Includes dual VAD (WebRTC + Silero) for robust voice detection
+#
+# Updated per RealtimeSTT PR #295:
+# - CUDA 12.8.1 (latest stable)
+# - PyTorch 2.7.1 with cu128 support
+# - Ubuntu 24.04 base
+# - Single Python 3.11 installation
 
-FROM nvidia/cuda:12.6.2-cudnn-runtime-ubuntu22.04
+FROM nvidia/cuda:12.8.1-cudnn-runtime-ubuntu24.04
 
 # Prevent interactive prompts during build
 ENV DEBIAN_FRONTEND=noninteractive
@@ -11,35 +17,23 @@ ENV PYTHONUNBUFFERED=1
 # Set working directory
 WORKDIR /app
 
-# Install system dependencies
+# Install system dependencies (Ubuntu 24.04 has Python 3.12 by default)
 RUN apt-get update && apt-get install -y \
-    python3.11 \
-    python3.11-venv \
-    python3.11-dev \
     python3-pip \
-    build-essential \
     ffmpeg \
     libsndfile1 \
     libportaudio2 \
-    portaudio19-dev \
     git \
     curl \
     && rm -rf /var/lib/apt/lists/*
 
-# Upgrade pip
-RUN python3.11 -m pip install --upgrade pip
+# Install PyTorch with CUDA 12.8 support (installed first for layer caching)
+COPY requirements-gpu-torch.txt .
+RUN python3 -m pip install --break-system-packages --no-cache-dir -r requirements-gpu-torch.txt
 
-# Copy requirements first (for Docker layer caching)
+# Copy and install other Python dependencies
 COPY requirements.txt .
-
-# Install Python dependencies
-RUN python3.11 -m pip install --no-cache-dir -r requirements.txt
-
-# Install PyTorch with CUDA 12.1 support (compatible with CUDA 12.6)
-RUN python3.11 -m pip install --no-cache-dir \
-    torch==2.5.1+cu121 \
-    torchaudio==2.5.1+cu121 \
-    --index-url https://download.pytorch.org/whl/cu121
+RUN python3 -m pip install --break-system-packages --no-cache-dir -r requirements.txt
 
 # Copy application code
 COPY stt_server.py .
@@ -52,7 +46,7 @@ EXPOSE 8766
 
 # Health check - use netcat to check if port is listening
 HEALTHCHECK --interval=30s --timeout=10s --start-period=120s --retries=3 \
-    CMD python3.11 -c "import socket; s=socket.socket(); s.settimeout(2); s.connect(('localhost', 8766)); s.close()" || exit 1
+    CMD python3 -c "import socket; s=socket.socket(); s.settimeout(2); s.connect(('localhost', 8766)); s.close()" || exit 1
 
 # Run the server
-CMD ["python3.11", "stt_server.py"]
+CMD ["python3", "stt_server.py"]
diff --git a/stt-realtime/requirements-gpu-torch.txt b/stt-realtime/requirements-gpu-torch.txt
new file mode 100644
index 0000000..f3187ca
--- /dev/null
+++ b/stt-realtime/requirements-gpu-torch.txt
@@ -0,0 +1,5 @@
+# PyTorch with CUDA 12.8 support
+# Updated per RealtimeSTT PR #295 for better performance
+torch==2.7.1+cu128
+torchaudio==2.7.1+cu128
+--index-url https://download.pytorch.org/whl/cu128