> ## Documentation Index
> Fetch the complete documentation index at: https://docs.talking-avatar.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Open Source overview

> A free, MIT-licensed 3D talking avatar for the browser. No server, no account, no API key.

Talking Avatar Open Source is a 3D talking avatar for the browser. Give it your own `.glb` avatar and an audio stream: a small model listens to the audio in the browser and drives the avatar's mouth, with natural blinks and brows. No text, no phoneme timings, no TTS-provider visemes, no server and no API key.

```js theme={null}
const avatar = new TalkingAvatar({ container, avatarUrl: "https://example.com/avatar.glb" });
avatar.attachStream(voiceAgentAudio);
```

> **[Quickstart](https://docs.talking-avatar.dev/open-source/quickstart.md)**
>
> Install the package and make your avatar talk.

> **[Try the 3D demo](https://talking-avatar.dev/demo/3d-avatar)**
>
> Sample voices in several languages, your own audio files, or your microphone.

## Features

* **Two inputs, one line each:** `attachStream(mediaStream)` for live audio, `speak(url | ArrayBuffer | Blob)` for clips.
* **Works with any voice source:** OpenAI, ElevenLabs, Azure, Fish Audio, Cartesia or any other TTS, WebRTC voice agents, or a microphone. The model only listens to the audio.
* **Runs entirely in the browser.** Audio never leaves the page. No API key, no server, no ML runtime.
* **Small:** 8 KB gzipped of code, plus a 1 MB model that's downloaded once. About 2% of one CPU core while speaking.
* **Anticipates sounds,** like a real speaker. Streams are delayed slightly so the mouth moves into each sound on time; clips are analysed in full before they play.
* **Any `.glb` avatar with Oculus visemes,** or map your own morph names. Framed as a face close-up (no arms or hands).
* **Natural blinks and brows** that follow what the avatar is doing: speaking, listening or thinking.
* **Framework-free core** plus a React component. TypeScript types included.

## What it is, and isn't

| It does | It doesn't |
| - | - |
| Animate the mouth, blinks and brows of your 3D avatar from audio you supply | Generate speech, or include an LLM |
| Play the audio itself, in sync with the mouth | Create or rig avatars, or turn a photo into an avatar |
| Run in the browser as a JavaScript API | Offer a hosted REST endpoint, or export MP4 video |
| Move the face | Move the head, gaze, arms or hands |

Want a photorealistic person instead of a 3D model? That's [Realistic Avatars](https://docs.talking-avatar.dev/realistic-avatars/overview.md), a separate, hosted product.

## License

The SDK and the lip-sync model are [MIT licensed](https://github.com/interviewflowai/talking-avatar/blob/master/LICENSE), Copyright (c) 2026 InterviewFlowAI: free for any use, commercial included, with modification and redistribution. Keep the copyright and permission notice with copies or substantial portions of the software.

There are no subscriptions, credits, per-minute fees, watermarks or usage quotas. Your avatar assets, audio, TTS and hosting are your own, under their own licences.

## Source code

[github.com/interviewflowai/talking-avatar](https://github.com/interviewflowai/talking-avatar). Issues and pull requests are welcome.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.