Audio Generation

SFX, voice, and music.

Generate SFX, voice, and music through the same submit, track, and download workflow as text and image. Live families: /capabilities/sound-effects, /capabilities/voice, and /capabilities/music.

One lifecycle for audio work

SFX, voice, and music jobs use the same submission, polling, and receipt conventions.

Protect long-running pipelines

Durable execution keeps audio generation independent from a single browser or editor request.

Centralize provider access

Keep audio-provider credentials and routing out of individual content tools.