WaveSpeedText to musicComing soon

wavespeed-ai/song-generation

Name: wavespeed-ai/song-generation
Brand: WaveSpeed

wavespeed-ai/song-generation is a text to music 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
`lyrics` required	text	—	Each paragraph represents a segment starting with a structure tag and ending with a blank line, each line is a sentence without punctuation, segments [intro], [inst], [outro] should not contain lyrics, while [verse], [chorus], and [bridge] require lyrics.
`seed`	number (whole)	—	The random seed to use for the generation. -1 means a random seed will be used.
`genre`	one of Pop, R&B, Dance, Jazz, Folk, Rock, Chinese Style, Chinese Tradition, Metal, Reggae, Chinese Opera, Auto	Auto	Genre Select (Optional). Choose a genre for the song.
`top_k`	number (whole) 1 to 100	50	The top-k value to use for the generation. This controls the number of highest probability vocabulary tokens to keep for top-k-filtering.
`description`	text	—	Song Description (Optional). Describe the gender, timbre, genre, emotion, instrument and bpm of the song. Only English is supported currently.
`temperature`	number 0.1 to 2	0.9	The temperature to use for the generation. A higher value means more randomness in the output.
`prompt_audio`	text	—	Prompt Audio (Optional). Provide a URL to an audio file that serves as a prompt for the genre of the song generation.
`guidance_scale`	number 0.1 to 3	1.5	The guidance scale to use for the 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": "wavespeed",
    "model": "wavespeed-ai/song-generation",
    "input": {
      "lyrics": "<lyrics>"
    }
  }'