StepFun Launches StepAudio 3 API for Real-Time Audio and Music
Key Info
StepFun has released the API for StepAudio 3, its new family of five audio models covering real-time voice, speech recognition, speech generation, audio generation, and music.
Highlights
- The official API link is now live, letting developers integrate StepAudio 3's real-time voice and speech capabilities.
- The family includes specialized models for speech recognition, speech generation, audio generation, and music.
- StepAudio 3's real-time model reportedly ranks #1 on Artificial Analysis for combined performance metrics.