Video models
Infinitalk API-AI lip-sync generator
On this page
Infinitalk API-AI lip-sync generator — high-quality AI video generation.
| modelId | infinitalk-from-audio |
| Modality | video |
| Pricing | See this model on the Pricing page for the current per-call price (with your markup). |
Operations
| Operation | modelId | Endpoint | Required input |
|---|---|---|---|
| Default | infinitalk-from-audio | POST /api/v1/generate | image_url, audio_url, prompt |
| Poll task | — | GET /api/v1/task/{id}?model=infinitalk-from-audio | — |
Input parameters
| Field | Type | Required | Values / example |
|---|---|---|---|
| image_url | string | Yes | URL of the input image. If the input image does not match the chosen aspect ratio, it is resized and center cropped. (image URL) |
| audio_url | string | Yes | Audio duration must not exceed 15 seconds. (image URL) |
| prompt | string | Yes | The text prompt to guide video generation. Max 5000 characters. (default: Subtle lifelike motion synced to the audio, gentle natural head movement and soft micro-expressions, calm even key light, smooth realistic delivery.) |
| resolution | string | No | Resolution of the video to generate. Must be either 480p or 720p. (options: 480p | 720p) (default: 480p) |
| seed | number | No | Random seed for reproducibility. Valid range is 10000 to 1000000. (range 10000-1000000) |
| nsfw_checker | boolean | No | A configurable parameter. Defaults to true in the Playground. (true/false) (default: true) |
Example request
bash
curl -X POST https://you.bot/api/v1/generate \
-H "Authorization: Bearer $YOUBOT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"modelId":"infinitalk-from-audio","input":{"image_url":"https://example.com/input.jpg","audio_url":"https://example.com/input.mp3","prompt":"A cinematic aerial shot of a coastal town at golden hour, gentle waves rolling onto the shore, warm light, slow camera push-in.","resolution":"480p","seed":10000,"nsfw_checker":true}}'