AI Music Generation API
Generate music from a text prompt with ElevenLabs or MiniMax through one endpoint, paid per call with no account.
2 models from 2 providers: MiniMax, ElevenLabs.
Models
Call it
The first response is 402 with the exact price and every way to pay. Pay,
repeat the request with the proof, and you get the result.
curl -X POST https://api.glianalabs.com/v1/music/generations \
-H 'content-type: application/json' \
-d '{"model":"music-v2","prompt":"warm lo-fi beat with soft piano, 90 bpm"}'How it works
POST /v1/music/generations takes a model and a prompt; length, instrumental-only and output format are model options listed by GET /v1/schema?model=<id>. The track is stored and returned as a URL.
Limits worth knowing
Each provider applies its own content rules, including on prompts that name artists. Audio URLs expire after 7 days, so download the tracks you keep.
Questions
How is AI music priced?
Per track or per second depending on the model, quoted from your request before you pay.
Can I make instrumentals?
Yes. ElevenLabs music-v2 has a force_instrumental option.
Is there a free tier?
No. Every call is paid individually, with no plan or minimum. A request that fails validation is refused before it runs, so it is never charged.
Do I need an account or an API key?
No. The first response is HTTP 402 with the exact price; pay it with USDC from your own wallet and repeat the request. To prepay instead, top up a balance in rupiah and send a gk_ key.