WaveSpeedText to audioComing soon

mirelo-ai/sfx-2.0/video-to-audio

Name: mirelo-ai/sfx-2.0/video-to-audio
Brand: WaveSpeed

mirelo-ai/sfx-2.0/video-to-audio is a text 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 URL. The video must be at least 1 second long.
`seed`	number (whole) 0 to 2147483647	—	Random seed. Leave empty for random generation.
`prompt`	text	—	Optional description of the sounds to generate.
`duration`	number 1 to 600	10	Requested sound duration in seconds; capped by the input video length.
`output_format`	one of wav, mp3, aac, flac	wav	Output audio format.
`negative_prompt`	text	—	Sounds to avoid, such as music, voices, or traffic.
`preserve_speech`	true or false	true	Keep existing speech while generating new sound effects.
`audio_bitrate_kbps`	number (whole) 32 to 320	—	Optional MP3 or AAC bitrate in kbps. Leave empty for automatic encoding.

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": "mirelo-ai/sfx-2.0/video-to-audio",
    "input": {
      "video": "<video>"
    }
  }'