ReplicateText to musicComing soon

minimax/music-cover

Name: minimax/music-cover
Brand: Replicate

minimax/music-cover is a text to music tool from Replicate 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.

Priced by usage

Pricing

$0.39 per audio file.

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
`prompt` required	text	—	A description of the target style for the cover. For example: 'R&B version, smooth vocal, groovy bass' or 'Hard rock, electric guitar riffs, powerful drums'. Up to 2000 characters.
`audio_url` required	text	—	URL of the song to cover. Must be a publicly accessible MP3 or WAV file.
`lyrics`	text		Optional lyrics to override the ones extracted from the source song. If not provided, the singer will sing the original song's lyrics. Use \n for line breaks and structure tags like [verse], [chorus], [bridge] to mark sections. Up to 3000 characters.
`bitrate`	JSON	256000	Bitrate for the generated music
`sample_rate`	JSON	44100	Sample rate for the generated music
`audio_format`	JSON	mp3	Audio format for the output

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": "replicate",
    "model": "minimax/music-cover",
    "input": {
      "prompt": "<prompt>",
      "audio_url": "<audio_url>"
    }
  }'