MeduxMedux

Video > Text & Image to Video

Text & Image to Video

Generate a video and audio from a text prompt with optional image, last-frame, and audio references.

POST/api/app/v1/generate/video/text_image_to_video

Examples

curl -X POST https://api.medux.io/api/app/v1/generate/video/text_image_to_video \
  -H 'Authorization: Bearer $MEDUX_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"height":832,"model_id":"text-image-to-video-default","num_frames":124,"num_inference_steps":9,"prompt_text":"Hello from Medux","resolution":"480p","seed":-1,"width":480}'

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

Prompt text used to generate the video and audio.

Location: BODY

prompt_image_file_idstringoptional

Optional reference image file_id.

Location: BODY

last_image_file_idstringoptional

Optional last-frame image file_id.

Location: BODY

prompt_audio_file_idstringoptional

Optional driving audio file_id. When set, generated video follows this audio.

Location: BODY

resolutionstringoptional

Target output resolution preset. Default: 480p.

Location: BODY

num_framesintegeroptional

Number of generated video frames when prompt audio is not set. Default: 124.

Location: BODY

num_inference_stepsintegeroptional

Number of diffusion inference steps. Default: 9.

Location: BODY

seedintegeroptional

Random seed. Use -1 to let the pipeline choose one. Default: -1.

Location: BODY

heightintegeroptional

Optional explicit output height. Default: 832.

Location: BODY

widthintegeroptional

Optional explicit output width. Default: 480.

Location: BODY

model_idstringoptional

Text and image to video model id. Default: text-image-to-video-default.

Location: BODY

titlestringoptional

Optional task title.

Location: BODY

Response

Response

application/json
codeint32optional

response code enums:
.. 0: ok
.. 12: invalid input
.. 1410: invalid model
.. 1409: paid plan required
.. 1401: insufficient credits
.... 1401 ~ 1499 是 media
.. 1404: provider error
.. 1405: provider timeout
.. 13: unauthenticated
.. 16: rate limit
.. 99: server error

Available options: 0 12 1410 1409 1401 1404 1405 13 16 99

Location: RESPONSE

data.assetobjectoptional

No description provided.

Location: RESPONSE

data.paid_plan_requiredobjectoptional

No description provided.

Location: RESPONSE

data.taskobjectoptional

No description provided.

Location: RESPONSE

messagestringoptional

No description provided.

Available options: ok invalid input invalid model paid plan required insufficient credits provider error provider timeout unauthenticated rate limit server error

Location: RESPONSE

MCP Tool

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

Text & Image to Video

Generate a video and audio from a text prompt with optional image, last-frame, and audio references.

Invocation Example

Generate a video and audio from a text prompt with optional image, last-frame, and audio references.