bytedance/seed-audio-1.0/text-to-audioByteDance's Seed Audio 1.0 text-to-audio turns one prompt into an MP3 scene of up to about two minutes, with several speakers' quoted lines plus music and sound effects. Up to three reference clips can reuse a voice, with speed, pitch and volume controls.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- 0:00 / –:––
morning-voice-note-same-voice The rainy-night voice note goes in as @Audio1, and the prompt asks for the same woman the next morning: a new message with new room sounds, written as a short script.
- 0:00 / –:––
rainy-window-voice-note One prompt builds the whole scene: a woman's breathless late-night voice message, with the rain and slow jazz piano the prompt asks for playing underneath, all in a single MP3 at a flat per-request price.
- 0:00 / –:––
hotel-bar-at-midnight A man and a woman trading lines in a hotel bar, their voices and the clinking glasses and lounge music the prompt asks for all generated from one text description rather than picked from a voice list.
- 0:00 / –:––
storm-cabin-audiobook A romance narration read by a warm male narrator, with the crackling fireplace and distant thunder the prompt asks for built into the same MP3, at the same flat per-request price.
This example starts at $0.36 per request. The Playground updates the estimate when you change the settings.