StepAudio 3 Realtime · empiriolabs

Speech in, speech out, over one socket. Interruptible mid-reply, with voice activity detection deciding when to answer.

Base modelAll models on this baseAll models of the providerto the provider

All StepFun models at every provider

Input, $/1M $1.50

Output, $/1M $10.00

Cache read $0.30

Cache write —

Context 262 144

Max output 131 072

Accepts audio, text

Last checked 04.11.2026 12:00:14 UTC

Source provider's page