Start generating

Generate audio from a video

Changed on

Generate synchronized sound effects for a video, optionally guided by a text description. Returns audio, not a video with a replacement soundtrack.

post/v1/video_to_audio

Request

  • Base URL
    https://api.dev.runwayml.com
  • URL
    https://api.dev.runwayml.com/v1/video_to_audio
  • Auth
    HTTP bearer

Headers

X-Runway-Version'2024-11-06' required

The version of the RunwayML API being used. You can read more about versioning here.

Request body

durationnumber required
negativePromptstring

Sounds to avoid in the generated audio.

numVariantsinteger

The number of audio variations to generate.

format'mp3' | 'wav' | 'flac'

The format of the generated audio.

seedinteger

A seed for reproducible generation.

promptTextstring

A description of the sound effects to generate.

preserveSpeechboolean

Whether to preserve dialogue from the input video. Disabling this does not guarantee speech-free output.

model'mirelo_sfx_2_0' required

Example request

{
  "videoUri": "https://example.com/video.mp4"
}

Response

The task that was created.

idstring uuid required

The ID of the task that was created. Use this to retrieve the task later.

Changes