WaveSpeedAudio to audioComing soon

wavespeed-ai/yue2-3b/music-to-music

Name: wavespeed-ai/yue2-3b/music-to-music
Brand: WaveSpeed

wavespeed-ai/yue2-3b/music-to-music is an audio 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
`audio` required	URL or file	—	Reference song audio URL.
`style` required	text	—	Describe the genre, mood, instruments, language and vocal style.
`lyrics` required	text	—	Song lyrics. Use section markers such as [Verse] and [Chorus].
`seed`	number (whole)	—	Random seed. Use -1 for a random seed.
`top_k`	number (whole) 1 to 32768	100	Number of most likely tokens considered when sampling music tokens.
`top_p`	number 0.01 to 1	0.95	Nucleus sampling probability for music generation. Lower values restrict sampling to more likely tokens.
`temperature`	number 0 to 5	1	Music generation sampling temperature. Higher values increase randomness; 0 uses greedy sampling. Does not change score planning.
`guidance_scale`	number 0 to 20	1	Text guidance strength during music generation. Higher values strengthen conditioning on the prompt; excessive values may reduce quality.

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": "wavespeed-ai/yue2-3b/music-to-music",
    "input": {
      "audio": "<audio>",
      "style": "<style>",
      "lyrics": "<lyrics>"
    }
  }'