What it does
TEN is an open-source framework for building conversational AI that listens and speaks in real time, like a voice assistant. It connects speech recognition, an AI model and a voice together with low delay.
Its example apps include a general voice assistant, a doodle board that draws what you describe, speaker labelling, animated talking avatars, phone-call agents and a transcription tool. It can even run on a small hardware board.
The quick-start examples rely on several online services, including Agora for live audio, OpenAI for the AI model, Deepgram for speech recognition and ElevenLabs for the voice, each needing its own key.
Who it's for
Developers building voice agents, talking avatars or real-time conversational apps.
Can I use it without coding?
Developers only. Setup uses Docker, configuration files and several API keys. New to this? Start here.
Can I run it?
- Cost
- Free, but needs an AI accountThe software is free, but it uses an online AI service (like OpenAI or Anthropic), which usually charges for use.
- Runs on
- Server, Cloud
- Computer
- An ordinary computer is fine
- Privacy
- Sends what you give it to an online service
- API key
- Needed. An API key is a password-like code from an online AI service. What's that?
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- No standard license listed. Check the GitHub page before using it for business.
- Keep your API key private. Never paste it into websites or share it, and set a spending limit with the AI service.
- What you type or upload is sent to an online service. Avoid sharing private or sensitive information.
- More on staying safe