Spiral gives your agent every tool with one account. Browse the tools →

falAudioAvailable now

Mirelo SFX2.0 · Video to Audio

mirelo-ai/sfx2.0/video-to-audio

Edit and transform audio with Mirelo SFX2.0 · Video to Audio from fal through one Spiral API key. It runs in the background and returns audio. Pay as you go, with no subscription.

Pricing

$0.0195 per second. Billed on duration, default 10.

Limits

Runs
In the background
Returns
audio
Longest queue wait
1 hour
Run deadline
30 minutes
Longest run, end to end
255 minutes
Largest inline input
1 MB
Largest input file
2 GB
Largest output
5 GB

Input

FieldKindDefaultDescription
video_url requiredURL or file—

Video to add sound to: an http(s) URL, or a base64 data URI up to 8 MB.

text_prompttext—

Optional text guiding the soundtrack. Name sounds the picture does not show, such as off-screen sounds or an ambience bed, to have them worked into it.

negative_prompttext—

Sounds to keep out of the result, as a short comma-separated list.

preserve_speechtrue or falsetrue

Keep the speech in the input's audio and generate the rest of the soundtrack around it. False generates sound effects only and suppresses speech.

durationnumber
1 to 600
10

Seconds of sound to generate, from 1 s to 600 s, clamped to the video's length. Over 10 s generates in 10 s windows. A video shorter than 1 s answers 400.

num_samplesnumber (whole)
1 to 4
2

Number of variations to generate. Billed per sample.

seednumber (whole)
-1 to 18446744073709552000
—

Seed for generation. -1 or None for random.

upload_audio_formatone of
wav, mp3, aac, flac
wav

Audio format of each file

upload_audio_bitrate_kbpsnumber (whole)
32 to 320
—

Bitrate in kbps for an mp3 or aac upload. mp3 is written at exactly this constant rate, one of 32, 40, 48, 56, 64, 80, 96, 112, 128, 160, 192, 224, 256, 320. aac takes 32 to 256 as a target the encoder may undershoot on mono or sparse audio. Unset keeps the default: mp3 at LAME V0 VBR, aac at a 256 kbps target. Refused with a lossless upload_audio_format.

return_speechtrue or falsefalse

Also return the input's separated speech as its own audio file, in the response's speech. With preserve_speech false the soundtracks are sound effects only and the speech is separated while they generate. With preserve_speech true it is the speech separated from the input that the soundtracks were generated around, not the speech in them: the model renders that speech anew, so the file does not cancel or double it cleanly when layered onto a soundtrack. The file is mono, in upload_audio_format, and as long as the soundtracks. It is not billed.

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": "mirelo-ai/sfx2.0/video-to-audio",
    "input": {
      "video_url": "https://di3otfzjg1gxa.cloudfront.net/chase.mp4"
    }
  }'

Frequently asked questions

How much does Mirelo SFX2.0 · Video to Audio cost?

$0.0195 per second. Billed on `duration`, default 10. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

How do I use Mirelo SFX2.0 · Video to Audio through an API?

Send `POST /v1/runs` with `"provider": "fal"`, `"model": "mirelo-ai/sfx2.0/video-to-audio"` and the input fields on this page, using one Spiral API key. It runs in the background: poll the run, or name a webhook to be told when it finishes.

Do I need an account with fal to use Mirelo SFX2.0 · Video to Audio?

No. Spiral runs it on its own fal account and charges your Spiral balance.

Can my AI agent use Mirelo SFX2.0 · Video to Audio?

Yes. Agents find and run it through Spiral's MCP server, CLI or agent skill, with the same API key.