# voice-chat-ai

> Self-hosted open-source voice chat app for talking to AI characters in a web UI or terminal, mixing Ollama and cloud LLMs with Spark-TTS, Kokoro or ElevenLabs voices.

- **Category:** AI Chat
- **Licence:** MIT
- **Latest version:** v1.4.1
- **Open source:** oss
- **Languages:** JavaScript, Python
- **Platforms:** Docker, Docker Compose, pip
- **Tags:** WebRTC, Openai, Ollama, Voice Chat, Text To Speech, Fastapi, Realtime, Speech To Text, Conversational Ai, Voice ai, Elevenlabs, Voice cloning, Xai, Selfhosted, Whisper Ai, Kokoro, Anthropic Claude, Ai Voice, Ai Speech, Elevenlabs Api, Ai Voice Agent, Typecast, Xai Tts, AI Characters

## Description

Voice Chat AI lets you hold spoken conversations with a large library of built-in AI characters (Einstein, a wizard, HAL 9000 and dozens more) through a FastAPI web UI or a feature-rich terminal CLI. Chat can go to Ollama, OpenAI, xAI or Anthropic models, while speech can be produced locally with Spark-TTS zero-shot voice cloning, Kokoro or Qwen3-TTS, or through cloud APIs from OpenAI, ElevenLabs, xAI, Typecast and Speechify; transcription defaults to OpenAI with an optional local Faster Whisper. It supports an OpenAI Enhanced mode with emotional TTS instructions, WebRTC-based OpenAI Realtime speech-to-speech conversations with natural interruption (or a self-hosted GA-compatible realtime server), mood-aware replies via sentiment analysis, spoken triggers that have the model describe your desktop, plus 15+ interactive games and immersive story adventures. You install it natively with Python 3.11+, ffmpeg and a virtualenv, or run the bigsk1/voice-chat-ai Docker image (base CPU or CUDA variant) with a .env file; the UI is served on port 8000. The maintainer recommends native installation over Docker because container audio requires PulseAudio/microphone mapping.

## Links

- [Homepage](https://github.com/bigsk1/voice-chat-ai)
- [Docker](bigsk1/voice-chat-ai)
- [Games Documentation](https://github.com/bigsk1/voice-chat-ai/blob/main/docs/games.md)
- [Stories Documentation](https://github.com/bigsk1/voice-chat-ai/blob/main/docs/stories.md)
- [Spark-TTS Documentation](https://github.com/bigsk1/voice-chat-ai/blob/main/docs/SPARKTTS.md)
- [OpenAI Enhanced demo video](https://youtu.be/TjHwVwzUUvM)
- [CPU-only CLI demo video](https://youtu.be/d5LbRLhWa5c)

---
Source: https://selfhost.directory/project/voice-chat-ai