> ## 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.

# Choose a product

> Realistic Avatars, Voice Agents and Open Source compared.

Talking Avatar has two avatar products, plus a no-code way to use the first one. They aren't tiers of one product: each shows a different kind of avatar and runs in a different place.

| | Realistic Avatars | Voice Agents | Open Source |
| - | - | - | - |
| **What it is** | Photorealistic avatars that speak **your** agent's voice | A complete AI voice agent on a realistic avatar | A 3D talking avatar for **your own** `.glb` model |
| **Who it's for** | Developers with a voice agent or TTS | Anyone, no code needed | Developers with 3D avatars |
| **The AI and the voice** | You bring them | Included | You bring them |
| **Where it renders** | Our servers, streamed as video | Our servers, streamed as video | The user's browser (WebGL) |
| **What moves** | Lips, natural expressions and subtle head motion | Lips, natural expressions and subtle head motion | Lips, blinks and brows (face close-up, no head motion) |
| **Price** | \$0.02 a minute, billed per second | \$0.06 a minute, billed per second | Free (MIT) |
| **Account and API key** | Required | Account required | Not needed |
| **Set up in** | Your code, with the SDK or the WebSocket API | The dashboard | Your code, with the SDK |
| **How users see it** | In your page, or in your LiveKit room | A share link, a website widget or an iframe | In your page |

## Realistic Avatars

Choose Realistic Avatars when you already have a voice agent, or a text-to-speech voice, and want a photorealistic person to speak it. You keep full control of the conversation: your server streams audio to the avatar, and your page (or your LiveKit room) shows it.

* Works with any TTS or speech-to-speech model.
* Interruptions are one call, and tell you how much of the reply was heard.
* Your API key stays on your server.

[Get started with Realistic Avatars →](https://docs.talking-avatar.dev/realistic-avatars/overview.md)

## Voice Agents

Choose Voice Agents when you want a talking AI agent without building one. You describe the agent in plain language, pick an avatar and a voice, and share it. The realtime AI model, speech recognition and voice are all included in the per-minute price.

* Templates for support, sales, interviews, reception and tutoring.
* Tools that call your HTTPS endpoints (or a Zapier, Make or n8n webhook) during the call.
* A transcript of every call, and a signed post-call webhook.
* Callers talk from their web browser. Phone calls aren't supported.

[Get started with Voice Agents →](https://docs.talking-avatar.dev/voice-agents/overview.md)

## Open Source

Choose Open Source when you have (or want) your own 3D avatars and prefer something free that runs entirely in the browser. Audio never leaves the page.

* A 1 MB lip-sync model that runs as plain JavaScript.
* Works with any audio: a TTS clip, a WebRTC voice agent, or a microphone.
* A framework-free core and a React component.

[Get started with Open Source →](https://docs.talking-avatar.dev/open-source/overview.md)

> [!NOTE]
>
> All three ship in one npm package, [`@interviewflowai/talking-avatar`](https://www.npmjs.com/package/@interviewflowai/talking-avatar). Realistic Avatars use its `/server` and `/live` imports. Open Source uses the root import and `/react`.


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