> ## Documentation Index > Fetch the complete documentation index at: https://mintlify.com/kyutai-labs/unmute/llms.txt > Use this file to discover all available pages before exploring further. # Welcome to Unmute > Transform text LLMs into voice-enabled conversational AI with real-time speech-to-text and text-to-speech Unmute Hero Light Unmute Hero Dark ## What is Unmute? Unmute is a complete system that allows text LLMs to listen and speak by wrapping them in Kyutai's state-of-the-art speech models. Experience natural voice conversations with any text LLM you like. Optimized STT and TTS models deliver \~450ms response time in production Works with any OpenAI-compatible LLM server - vLLM, Ollama, OpenAI, Mistral Stream audio and text bidirectionally over WebSocket connections Clone voices from audio samples and customize character personalities ## How It Works Unmute orchestrates multiple AI services to create seamless voice conversations: ```mermaid theme={null} graph LR UB[User Browser] UB --> B(Backend) UB --> F(Frontend) B --> STT(Speech-to-text) B --> LLM(LLM) B --> TTS(Text-to-speech) ``` Audio is captured in the browser and streamed to the backend via WebSocket Kyutai STT transcribes speech in real-time with 6-token delay for low latency Your chosen text LLM generates a response based on the conversation history Kyutai TTS converts the response to speech with customizable voices Generated audio streams back to the browser for immediate playback ## Key Components The core orchestration layer that manages: * WebSocket connections with OpenAI Realtime API compatibility * Conversation state and chat history * Service coordination between STT, LLM, and TTS * Voice management and cloning Located in `unmute/main_websocket.py` Low-latency speech recognition: * Model: Kyutai STT 1B (English/French) * Memory: \~2.5GB VRAM * Latency: 6-token delay for real-time transcription * Architecture: Transformer with 16 layers, 2048 d\_model Natural voice synthesis: * Model: Kyutai TTS 1.6B (English/French) * Memory: \~5.3GB VRAM * Features: Voice cloning from audio samples * Voices: 100+ community-donated voices available Any OpenAI-compatible text model: * Default: Llama 3.2 1B Instruct (16GB config) * Recommended: Mistral Small 3.2 24B, Gemma 3 12B * Memory: 6.1GB VRAM minimum (model dependent) * Hosted via vLLM, Ollama, or external APIs Modern web interface: * Real-time audio capture and playback * WebSocket communication * Subtitles and debug mode (press 'S' and 'D') * Character selection and voice customization ## Deployment Options **Recommended** - Single GPU, single machine, very easy setup Manual service management for 1-3 GPUs across 1-5 machines Production scaling for 1-100 GPUs (used by unmute.sh) ## Model Architecture ### STT Model Configuration The speech-to-text model uses a transformer architecture optimized for streaming: ```toml theme={null} [modules.asr.model.transformer] d_model = 2048 num_heads = 16 num_layers = 16 dim_feedforward = 8192 causal = true max_seq_len = 40960 asr_delay_in_tokens = 6 # Low latency configuration ``` ### TTS Model Configuration The text-to-speech model supports voice cloning and multiple languages: ```toml theme={null} [modules.tts_py.py] cfg_coef = 2.0 # Classifier-free guidance coefficient n_q = 24 # Number of quantization levels padding_between = 1 # Token padding for prosody ``` ## Performance Metrics On unmute.sh with separate GPUs for each service: * **TTS Latency**: \~450ms (vs. \~750ms on single L40S GPU) * **Max Concurrent Users**: 4 per backend instance (GIL constraint) * **Model Memory**: 16GB VRAM total (STT: 2.5GB, TTS: 5.3GB, LLM: 6.1GB+) ## Try It Now Experience Unmute live at [unmute.sh](https://unmute.sh) or deploy your own instance: Get Unmute running locally in 5 minutes with Docker Compose Check hardware, software, and configuration prerequisites ## Research & Development Read the academic paper on delayed streams modeling Use Kyutai STT or TTS independently in your projects Unmute requires: * **GPU**: CUDA-capable with 16GB+ VRAM * **Architecture**: x86\_64 only (no aarch64 support) * **OS**: Linux or Windows with WSL (no native Windows or macOS) ## Community Unmute includes 100+ voices donated by the community through the [Unmute Voice Donation Project](https://unmute.sh/voice-donation) (June 2025 - February 2026). These voices are available for use with Kyutai TTS and other open-source TTS models. Browse available voices in the [voice repository](https://huggingface.co/kyutai/tts-voices). This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.