# Ojin Documentation

## Ojin Public Docs

- [Welcome](https://docs.ojin.ai/getting-started/readme.md): Build AI Agents That Feel Human. In Minutes.
- [Quickstart](https://docs.ojin.ai/getting-started/quickstart.md): Get up and running with Ojin in minutes.
- [Get your API key](https://docs.ojin.ai/getting-started/authentication.md)
- [REST API](https://docs.ojin.ai/getting-started/api.md)
- [Support](https://docs.ojin.ai/getting-started/support.md)
- [Data Deletion](https://docs.ojin.ai/getting-started/data-deletion.md)
- [Human Agent](https://docs.ojin.ai/apps/overview.md): Ojin's star product, give your AI agent a face. A lifelike visual avatar that speaks, listens, and expresses emotion with real-time synchronized animation, embedded with a single line of code.
- [Create & Configure](https://docs.ojin.ai/apps/overview/configure.md): Set up your Human Agent in the Ojin dashboard. Pick a mode, configure appearance and behaviour, and publish it.
- [Knowledge](https://docs.ojin.ai/apps/overview/knowledge.md): Give your Human Agent your organization's documents to answer from, in its prompt or by searching them during a conversation.
- [Tools & Events](https://docs.ojin.ai/apps/overview/tools.md): Let your Human Agent call functions during a conversation, and react to the agent from your own page.
- [Widget Integration](https://docs.ojin.ai/apps/overview/widget-integration.md): Embed a fully interactive Human Agent on your website with a single HTML tag.
- [Session API Reference](https://docs.ojin.ai/apps/overview/api-reference.md): Start agent sessions programmatically. The widget uses this API automatically, call it directly for custom integrations.
- [Introduction](https://docs.ojin.ai/models/introduction.md)
- [Get started](https://docs.ojin.ai/models/introduction/integrations.md)
- [API reference](https://docs.ojin.ai/models/introduction/api.md)
- [Using a Persona Template](https://docs.ojin.ai/models/introduction/using-persona-template.md)
- [Creating a custom persona](https://docs.ojin.ai/models/introduction/creating-persona.md)
- [Human Portrait](https://docs.ojin.ai/models/human-portrait.md): A cost-effective, lifelike persona model that transforms reference images into natural animated personas
- [Best practices](https://docs.ojin.ai/models/human-portrait/best-practices.md)
- [Human Presence](https://docs.ojin.ai/models/human-presence.md): Our flagship face model, a fully expressive, generative presence that goes beyond lip-sync.
- [Best practices](https://docs.ojin.ai/models/human-presence/best-practices.md)
- [Python SDK](https://docs.ojin.ai/models/build-with-python-sdk.md): Drive Ojin's face models (Human Presence and Human Portrait) straight from Python. Feed in your TTS audio; get back a synchronized, lip-synced talking-avatar stream.
- [Best Practices](https://docs.ojin.ai/models/build-with-python-sdk/python-sdk-best-practices.md): The key things to get right for a smooth, low-latency avatar pipeline with OjinSTVClient, whether you're prototyping straight to a browser, relaying media over WebRTC, or publishing directly into a Li
- [Direct WebRTC (LiveKit & Daily)](https://docs.ojin.ai/models/build-with-python-sdk/python-sdk-webrtc.md): Publish avatar audio and video directly into your LiveKit or Daily room. Avoid relaying avatar frames through your backend while keeping TTS input and control over WebSocket.
- [Optimizing Performance](https://docs.ojin.ai/guides/optimizing-performance.md): How to feed audio and play back frames for stable, low-latency lip-sync, and how the Python SDK and Pipecat handle most of it for you.
- [Troubleshooting](https://docs.ojin.ai/guides/troubleshooting.md): Common symptoms when building real-time avatars, with their cause and fix.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
This site has an agentic ask interface you may use to query the documentation dynamically by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.ojin.ai/index.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
