post
https://platform.perso.ai/api/studio/v1/task/stf/
Create a new Speech-to-Face (STF) task to generate avatar video.
Request Parameters
| Parameter | Required | Description |
|---|---|---|
agent | Yes | Agent identifier |
stf_model_style | Yes | Avatar model style name |
stf_input_audio | Yes | Audio file (binary upload) |
stf_start_frame | No | Starting frame number (default: 0) |
stf_video_profile | No | Quality: good, better, best |
stf_face_only | No | Render face only (default: false) |
stf_video_codec | No | Codec: h264_fmp4, vp9_webm |
webhook_url | No | URL for completion callback |
Request Format
Upload the audio file as multipart/form-data.
Example
Select "STFTaskRequestExample" or "STFTaskRequestExampleWithWebhook" from the Examples dropdown.