falVideo to videoComing soon

fal-ai/thinksound/audio

Name: fal-ai/thinksound/audio
Brand: fal

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

This tool is listed but not yet available to run.

Priced by usage

Pricing

$0.0013 per second. Measured from the input file. The final charge comes from usage.

Limits

Runs: In the background
Returns: audio, video
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_url` required	URL or file	—	The URL of the video to generate the audio for.
`prompt`	text		A prompt to guide the audio generation. If not provided, it will be extracted from the video.
`seed`	number (whole)	—	The seed for the random number generator
`num_inference_steps`	number (whole) 2 to 100	24	The number of inference steps for audio generation.
`cfg_scale`	number 1 to 20	5	The classifier-free guidance scale for audio generation.

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": "fal",
    "model": "fal-ai/thinksound/audio",
    "input": {
      "video_url": "https://storage.googleapis.com/falserverless/example_inputs/thinksound-input.mp4"
    }
  }'