Vox – Local Voice AI Framework in Rust (STT and TTS and VAD)
SMRTR summary
Vox is an open-source voice AI framework that runs entirely locally without cloud dependencies. It combines speech-to-text via Whisper models, text-to-speech through multiple engines including Kokoro and Pocket, and voice chat integration with Ollama LLMs. The framework offers CLI tools, web interface, Python bindings, and HTTP/WebSocket APIs for easy integration.
SMRTR provides this summary for quick context. The original article belongs to Hacker News.
Read the original article