TEN-Agent
Open-source real-time voice-interaction agent platform — the "agent framework" for voice
An open-source real-time voice-interaction AI agent platform based on TEN Framework — the "agent development framework" for voice.
Voice AI: lifelike TTS, accurate ASR, and real-time voice agents.
Key features
- Open-source framework for real-time multimodal conversational AI
- Agent examples: voice assistant, diarization, lip-sync avatars, SIP calls
- Extensions for memory, VAD and turn detection
- Runs on ESP32 hardware and deploys with Docker
Good for
- Developers building real-time voice assistants
- Teams prototyping conversational AI with ready-made examples
Stack & tags
Node.jsDockervoice-assistantconversational-aireal-timemultimodalframeworkdocker
Quick start
cd ai_agents
cp ./.env.example ./.env
# set API keys in .env, then follow the Docker build stepsFrom the project README on GitHub.
Similar open-source projects
Dia
★ 19,393Ultra-realistic conversational TTS from Nari Labs — multi-speaker dialogue in one pass
NVIDIA PersonaPlex
★ 10,588NVIDIA's 7B full-duplex voice conversation model — customizable voices and personas