Seed Audio 1.0

Audio creation model that treats sound as a unified scene: speech with emotional range and voice consistency, sound effects and ambience in one pass, 100 ms dialogue timing control, 20+ languages, up to 2 minutes per generation with continuation, voice creation from a text description or a reference sample. Vendor announcement 2026-07-20, available via BytePlus.

Understands

text, audio

Produces

speech, sound effects

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.