KoljaB/RealtimeVoiceChat

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

3832 stars · 456 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A Python client-server application enabling natural spoken conversations with LLMs, streaming browser audio via WebSockets through RealtimeSTT, a pluggable LLM backend (Ollama/OpenAI), and RealtimeTTS back to the browser. It focuses on low latency with interruption handling and dynamic turn detection.

Use cases

• talk to an AI with my voice in real time
• build a voice assistant with speech-to-text and text-to-speech
• run a local voice chatbot with Ollama
• low-latency spoken conversation with an LLM
• voice interface for chatting with AI models
• self-hosted real-time voice chat server

When to choose

• you want a ready-made, self-hostable voice chat pipeline with STT, LLM, and TTS wired together
• you need interruption handling and adaptive turn-taking in spoken conversations
• you prefer pluggable backends like Ollama or OpenAI and multiple TTS engines

When to avoid

• you need actively maintained software with guaranteed support - the author has stepped back to community-driven maintenance
• you need a production-grade, licensed product - there is currently no license file
• you only need text-based chat without audio

Facets

application · maturity maintenance

speech-recognition tts llm-inference websocket chatbot audio-processing artificial-intelligence large-language-models speech-processing chatbots web-development python cross-platform voice-assistant realtime stt tts ollama fastapi voice-chat low-latency docker web-server linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="KoljaB/RealtimeVoiceChat")