TEN Framework
An open-source framework for building real-time, multimodal conversational voice AI agents, with example agents, voice activity detection, turn detection and deployment tooling.
TEN Framework is an open-source framework for real-time, multimodal conversational AI. It is the core of a wider TEN ecosystem that also includes ready-made agent examples, a voice activity detector (VAD), a turn-detection component, and a Portal.
Agent examples include a low-latency, multi-purpose voice assistant meant as a starting point for building conversational agents; they can be run locally or in GitHub Codespaces for a quick start, and self-hosted with Docker or deployed to other cloud services. The project's documentation is available in English, Simplified Chinese, Japanese, Korean, Spanish, French and Italian.