Open-source realtime voice AI with streaming STT, browser VAD, interruptible TTS, and a typed WebSocket gateway for OpenAI-compatible models.

0 stars 1 forks 0 watchers TypeScript MIT License
audio llm nextjs openai realtime-ai self-hosted speech-to-text streaming text-to-speech typescript voice-activity-detection voice-ai websocket
3 Open Issues Need Help Last updated: Jul 10, 2026

Open Issues Need Help

View All on GitHub
help wanted good first issue area:observability

Open-source realtime voice AI with streaming STT, browser VAD, interruptible TTS, and a typed WebSocket gateway for OpenAI-compatible models.

TypeScript
#audio#llm#nextjs#openai#realtime-ai#self-hosted#speech-to-text#streaming#text-to-speech#typescript#voice-activity-detection#voice-ai#websocket
documentation help wanted good first issue

Open-source realtime voice AI with streaming STT, browser VAD, interruptible TTS, and a typed WebSocket gateway for OpenAI-compatible models.

TypeScript
#audio#llm#nextjs#openai#realtime-ai#self-hosted#speech-to-text#streaming#text-to-speech#typescript#voice-activity-detection#voice-ai#websocket
enhancement help wanted good first issue

Open-source realtime voice AI with streaming STT, browser VAD, interruptible TTS, and a typed WebSocket gateway for OpenAI-compatible models.

TypeScript
#audio#llm#nextjs#openai#realtime-ai#self-hosted#speech-to-text#streaming#text-to-speech#typescript#voice-activity-detection#voice-ai#websocket