StepFun · Music
Stepaudio 3 Realtime Preview
Speech in, speech out, over one socket. Interruptible mid-reply, with voice activity detection deciding when to answer.
Evidence and sources
International API storefront (platform.stepfun.ai) is Singapore-based; principal operating entity 上海阶跃星辰智能科技股份有限公司 (Shanghai).
Maker HQ: CN (source)
Sources: StepFun API data, EmpirioLabs dataPrimary data from StepFun API
from EmpirioLabs: primary mode, description
Input & output
from the model's typeText
Audio
Also known as: stepaudio-3-realtime
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works