# Avaturn.Live

## Docs

- [Create Session](https://docs.avaturn.live/api-reference/create-session.md): Initiates a session.
- [Create Speech Task](https://docs.avaturn.live/api-reference/create-speech-task.md): Adds the text to the avatar speech queue. If the avatar is already speaking, the text fragment is queued to be spoken at a later time. Nothing is said until you connect or while you're disconnected.
- [API Reference](https://docs.avaturn.live/api-reference/introduction.md): Create, manage, and terminate avatar sessions from your backend.
- [Terminate Session](https://docs.avaturn.live/api-reference/terminate-session.md): Terminates the session. If the avatar is still talking, it kills the session anyway.
- [Cartesia conversation engine](https://docs.avaturn.live/howtos/cartesia.md): Connect an Avaturn avatar to a deployed Cartesia Line agent.
- [External conversation engine](https://docs.avaturn.live/howtos/external.md): Drive an Avaturn avatar from your own WebSocket service — bring your own stack.
- [OpenAI Realtime engine](https://docs.avaturn.live/howtos/openai_realtime_api.md): Voice-to-voice avatar powered by the OpenAI Realtime API.
- [Introduction](https://docs.avaturn.live/introduction.md): Real-time conversational video avatars for the web.
- [Streaming LLM output (legacy)](https://docs.avaturn.live/legacy/llm-streaming.md): Legacy: pipe an LLM stream into the text-echo task endpoint. Use a conversation engine instead.
- [React demo (legacy)](https://docs.avaturn.live/legacy/react-example.md): React integration with Echo / GPT-4 text-echo flow.
- [Text echo (legacy)](https://docs.avaturn.live/legacy/text-echo.md): Legacy server-driven speech: push text, avatar speaks it. Not recommended for new integrations.
- [Quickstart](https://docs.avaturn.live/quickstart.md): Voice-to-voice avatar in 5 minutes with OpenAI Realtime.
- [Example](https://docs.avaturn.live/rest/example.md): End-to-end backend session lifecycle with the OpenAI Realtime engine.
- [REST Integration Guide](https://docs.avaturn.live/rest/integration-guide.md): Session lifecycle from your backend.
- [Web SDK Integration Guide](https://docs.avaturn.live/web-sdk/integration-guide.md): Mount the avatar in your frontend and wire up events.
- [Events](https://docs.avaturn.live/web-sdk/reference/events.md): Events emitted by the AvaturnHead instance.
- [Methods](https://docs.avaturn.live/web-sdk/reference/methods.md): Methods exposed by the AvaturnHead instance.
- [Properties](https://docs.avaturn.live/web-sdk/reference/properties.md): Constructor signature and configuration options for AvaturnHead.

## OpenAPI Specs

- [openapi](https://api.avaturn.live/api/v1/openapi.json)