ByteDance Volcano Engine launches Doubao real-time voice model 3.0 API in invite-only testing

火山引擎上线豆包实时语音模型3.0 API 服务，开启邀测

Doubao real-time voice model 3.0 (Seeduplex) is a native full-duplex end-to-end voice model. It claims three strengths: precise instruction following, noise resistance, and dynamic turn-taking. It stays quiet in multi-person conversations and only joins when a specified topic comes up. It can also call custom tools during real-time interaction to schedule calendar events or send emails. False replies and false interruptions are significantly reduced. Turn-taking latency dropped by about 250ms, the interruption rate in complex scenarios fell by 40%, and user-initiated interruption latency dropped by about 300ms. Target use cases include car cockpits, smart hardware, and customer service. The post does not disclose pricing or a public launch date.

Why it matters: ByteDance's first full-duplex end-to-end voice model in public beta, with concrete latency and anti-interference numbers — not pure marketing. Deduction: invite-only, no pricing or scale disclosed yet, real-world performance unverified.