MeduxMedux

Generate > Create Image Audio Driven Video

Create Image Audio Driven Video

Generate a talking video from a reference image, driving audio, and prompt text.

POST/api/app/v1/generate/video/image_audio_driven

Examples

curl -X POST https://api.medux.io/api/app/v1/generate/video/image_audio_driven \
  -H 'Authorization: Bearer $MEDUX_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model_id":"image-audio-driven-video-default","prompt_audio_file_id":"AUDIO_FILE_ID","prompt_image_file_id":"FILE_ID","prompt_text":"Hello from Medux","resolution":"720p"}'

Auth Requirements

Authentication is required via Authorization header.

Preconditions

Upload the source file and create a file reference before calling this endpoint.

Successful requests return a Medux task record immediately. Use the task query or sync endpoints to track completion.

All file inputs must be uploaded and persisted as file references before submission.

Request

Body

application/json
Authorizationstringrequired

Bearer token or API key.

Location: HEADER

prompt_textstringrequired

Talking prompt text used to guide video generation.

Location: BODY

prompt_image_file_idstringrequired

Reference image file_id.

Location: BODY

prompt_audio_file_idstringrequired

Driving audio file_id.

Location: BODY

resolutionstringoptional

Prompt image or prompt video frame resize target before generation. Default: 720p.

Location: BODY

model_idstringoptional

Image audio driven video model id. Default: image-audio-driven-video-default.

Location: BODY

titlestringoptional

Optional task title.

Location: BODY

Response

Response

application/json
No response fields documented for this endpoint.

MCP Tool

This endpoint is also available through the Medux-hosted remote MCP service.

Create Image Audio Driven Video

Generate a talking video from a reference image, driving audio, and prompt text.

Invocation Example

Generate a talking video from a reference image, driving audio, and prompt text.