Model releaseModerate global significanceConfirmed confidence
ByteDance Seed releases Seed LiveInterpret 2.0
ByteDance Seed releases the end-to-end speech-to-speech interpretation model Seed LiveInterpret 2.0 and says it is publicly available through Volcano Engine.
What happened
Event details
The model uses a full-duplex speech understanding and generation framework to produce translated audio while receiving speech. Official materials say it supports Chinese-English simultaneous interpretation, multi-speaker scenarios and zero-shot real-time voice cloning.
Assessment
Why it matters
A published model record with a documented capability or availability change.
63/100Global significance score. Regional effects are recorded only when the evidence supports a meaningful difference.
Availability
Access notes
Publicly available through Volcano Engine.