WaveSpeedVideo to audioComing soon

sonilo/v1/video-to-video-sound

Name: sonilo/v1/video-to-video-sound
Brand: WaveSpeed

sonilo/v1/video-to-video-sound is a video to audio tool from WaveSpeed that runs in the background and returns audio. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Price pending

Pricing

Price pending.

Limits

Runs: In the background
Returns: audio
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`video` required	URL or file	—	Input video. Supports MP4, MOV, WEBM, M4V, and GIF. Maximum duration is 180 seconds and maximum file size is 300 MB.
`segments` required	JSON	—	Optional time-aligned sound-effect prompts. When supplied, segments must begin at 0, be continuous, and not exceed the source video duration.
`ducking`	true or false	true	Lower generated music and sound effects while speech is present. Ignored when preserve_speech is enabled.
`sfx_prompt`	text	—	Optional overall prompt describing the generated sound effects.
`music_prompt`	text	—	Optional prompt describing the generated music.
`preserve_speech`	true or false	false	Preserve speech in the input video. When enabled, ducking is ignored.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "wavespeed",
    "model": "sonilo/v1/video-to-video-sound",
    "input": {
      "video": "<video>",
      "segments": {}
    }
  }'