Modelsslug: doubao-seedrealtime-1-0

Doubao SeedRealtime 1.0

豆包实时音视频通话模型 SeedRealtime 1.0

End-to-end omni-modal realtime model unifying audio, video and temporal signals for see-listen-speak interaction.

Curated Intelligence

1 items · Page 1/1
IT之家 · 智能时代T2·Models
78 pts
ByteDance Rolls Out Doubao SeedRealtime 1.0 Omni-Modal API

Volcano Engine has launched the API for Doubao SeedRealtime 1.0, an end-to-end omni-modal model that unifies audio, video and temporal signals for real-time see-listen-speak interaction. Compared with cascaded ASR+VLM+TTS pipelines, it cuts latency stacking and information loss, halves dialogue rhythm issues, and adds proactive expression plus noise robustness.