Generate music
Submits an asynchronous music generation job (an original song or instrumental track from a text description) to the fal.ai queue and returns the queued job immediately. Use it for soundtracks, background beds, jingles and intros; for spoken words use POST /v1/audio/generate. Poll GET /v1/jobs/{id} or GET /v1/audio/{id} for status; the finished track is result.audio. Credits are charged only when the job completes successfully.
Authorizations
API key in the format: Bearer {api_token}
Headers
Makes this write safe to retry: a repeat with the same key replays the first response instead of creating a second resource. Scoped to the account, remembered for 24 hours; reusing a key with a different payload is an error.
255Body
Model-specific input, forwarded to fal verbatim. prompt is required. Tracks come back at the model's own length; trim and fade them to fit.
A quality tier (fast, balanced, quality) or any fal.ai text-to-music endpoint id. Prefer a tier — it tracks the best current model for that price point. Defaults to fal-ai/lyria3/pro; GET /v1/audio/music/models maps tiers to ids with live pricing.
"fast"
"balanced"
"quality"
"minimax/music-3"
"fal-ai/lyria3/pro"
"mureka/api/generate/instrumental"
Response
Generation job queued
queued, processing, completed, failed, cancelled 
