SeedRealtime

Native audio-visual full-duplex model that watches, listens and speaks at once in a single architecture, without separate ASR and TTS stages. Shipped in the Doubao app.

объявлено 05.08.2026 подразделением ByteDance Seed

Understands

text, audio, video

Produces

text, speech

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.