For developers & agencies
Avatar API
Generate videos from text or your own recording, or give your voice agent a face. Connect with LiveKit, your app or your automation workflow.
Choose the output your app needs.
Generated video
A standard POST /inference takes text or an uploaded recording and returns JSON with video URLs for playback and download.
Streaming
The public API's ?stream=true returns MP4 data, not JSON. WebSocket endpoints support ongoing avatar streams.
LiveKit
Add a face to your existing voice agent with the Python plugin documented by LiveKit. This is a live conversation, not a generated video file.
Read the LiveKit integration guide →Lip-sync to your own recording
curl -X POST https://api.avatartalk.ai/inference \ -H "Authorization: Bearer $KEY" \ -F "audio=@speech.wav" \ -F "avatar=european_woman" \ -F "emotion=neutral"
WAV, MP3, M4A or OGG up to 5 minutes. Each started second of the recording costs one credit. The playground generates video files. Streaming uses the public API or LiveKit integration, not the panel's /api/inference endpoint. See the docs for supported avatars and languages.
Plug into the tools you already use.
API reference
Request format, authentication and responses.
Read the docs →GitHub examples
Working code to adapt to your application.
Browse examples →Make.com
Generate avatar videos in your scenarios.
See the integration →n8n
Add avatar video to your automation workflows.
See the integration →LiveKit Agents
Real-time avatar conversations for your agents, separate from video generation.
View the plugin →Make your first avatar video.
Try it in the browser. Connect your code when you are ready.