Generate > Create Audio Driven Video

Create Audio Driven Video

Generate an avatar video by pairing a reusable avatar with an uploaded audio file.

POST/api/app/v1/generate/video/audio_driven

Examples

curl -X POST https://api.medux.io/api/app/v1/generate/video/audio_driven \
  -H 'Authorization: Bearer $MEDUX_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"aspect_ratio":"ASPECT_RATIO","audio_file_id":"AUDIO_FILE_ID","avatar_asset_id":"AVATAR_ASSET_ID","clarity":"CLARITY","duration_seconds":1,"links":["https://example.com/reference"],"model":"MODEL","model_id":"MODEL_ID","title":"Demo title"}'

Media Samples

Approved examples for understanding request inputs, response shape, and official example output.

Official audio-driven talking video

This example uses talking-video-audio-standard.

Sample request

Generate a talking video from an official avatar and uploaded narration audio.

avatar_asset_idofficial_avatar_demo_001audio_file_id{audio_file_id}duration_seconds7clarity1080Paspect_ratio16:9model_idtalking-video-audio-standard

Sample response

Official example output for preview only. It is not a user Media Result.

output_urlOfficial example video output

Example output

Auth Requirements

Authentication is required via Authorization header.

Preconditions

Prepare avatar and audio assets before calling this endpoint.

Requires avatar_asset_id from your Media Assets or official public assets, plus audio_file_id.

Also accepts optional duration_seconds, links, clarity, aspect_ratio, and model.

Request

Body

application/json

Authorizationstringrequired

Bearer token or API key.

Location: HEADER

aspect_ratiostringoptional

Requested output aspect ratio, such as 16:9 or 9:16.

Location: BODY

audio_file_idstringrequired

No description provided.

Location: BODY

avatar_asset_idstringrequired

Reusable avatar asset ID owned by the current user or listed as an official public asset.

Location: BODY

claritystringoptional

Requested output resolution label, such as 1080P or 2K.

Location: BODY

duration_secondsint32optional

Requested output duration, in seconds.

Location: BODY

linksarray<string>optional

Optional reference links submitted from the Playground form.

Location: BODY

modelstringoptional

Generation model label or version selected in the Playground form.

Location: BODY

model_idstringoptional

Stable public Medux model identifier.

Location: BODY

titlestringoptional

No description provided.

Location: BODY

Response

application/json

codeint32optional

Application response code.

Code	Meaning
`0`	OK
`12`	Invalid input
`1401`	Insufficient credits
`1402`	Asset category does not match this operation
`1404`	Provider returned an error
`1405`	Provider request timed out
`13`	Authentication is required
`16`	Rate limit exceeded
`99`	Server error

Available options: 0 12 1410 1409 1401 1402 1407 1408 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 asset category mismatch asset locked asset expired 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.

Video / Audio-Driven Lip Sync

Create an avatar video from a source audio file and reusable avatar.

Invocation Example

Create a 7 second 1080P 16:9 talking video using avatar_asset_id {avatar_asset_id} and audio_file_id {audio_file_id}. Use model_id talking-video-audio-standard.

medux_video_create_audio_drivenResult: video

avatar_asset_id{avatar_asset_id}audio_file_id{audio_file_id}model_idtalking-video-audio-standard

On this page