Music Generation API - BudgetPixel API

Text or lyrics → song, video → soundtrack. Full songs with vocals from a style prompt and your own lyrics, instrumentals and background music of an exact length, or a soundtrack composed for a video you supply. Each model has its own endpoint, POST /v1/audios/{model}.

Models

6 models. Each name opens its API reference with every parameter.

Model	Maker	What it does
Music 3.0 `music-3.0`	MiniMax	The latest MiniMax music model: full-length songs from a style prompt and/or your own lyrics.
Music 2.6 `music-2.6`	MiniMax	Full-length songs from a style prompt and/or your own lyrics.
Lyria 3 `lyria-3`	Google	High-fidelity music from a text prompt, with optional lyrics and up to 10 reference images to condition the mood.
Mureka V9 `mureka-v9`	Mureka	Songs that sing your exact lyrics (structural tags like [verse]/[chorus] supported) with a vocal gender preference, or instrumental/BGM tracks from a prompt.
Sonilo Music `sonilo-music`	Sonilo	Licensed instrumental and background music of an exact length (5-360 seconds) from a text prompt: soundtracks for videos, ads, apps and games.
Sonilo Video Music `sonilo-video-music`	Sonilo	A licensed soundtrack composed for an input video (up to 6 minutes): the music follows the clip’s content, pacing and mood.

Need a ready-made track? Search the free stock music library first.

How a request works

Send POST /v1/audios/{model} with your prompt, lyrics or video. The response returns a job id right away.
Poll GET /v1/audios/{job_id} until status is succeeded. The response then holds the track’s URL.

Async jobs covers job statuses and errors.

Pricing

GET /v1/models?type=audio returns current prices, and POST /v1/cost quotes a request before you send it. You pay only for jobs that succeed; see Pricing & credits.