StepFunWeights not listed·Not published context·— params
StepAudio 3 Gen Previewstepfun/stepaudio-3-gen-preview
StepAudio 3 Gen Preview generates audio scenes from text and audio references, combining dialogue, sound effects, ambience and music in one clip.
Availability and billing notes
Reviewed September 21, 2026 · check the linked provider documentation for later changes.
Model ID stepaudio-3-gen-preview; POST /v1/audio/generate. Prompts can describe characters, scripts and sound design.
The official pricing page lists a limited-time free preview as of September 21, 2026. StepFun says the preview ID will be retired when a paid version launches; this is not a permanent free-tier promise.
Capabilities
- audio_generation
- speech_generation
Technical specs
- Context
- Not published
- Max output
- —
- Parameters
- —
- Release
- —
- Training cutoff
- —
- License
- —
Similar models
Compare with
- StepAudio 3 Gen Preview vs Qwen3.8 LiveTranslate Flash RealtimeComparison planned — not yet published
- StepAudio 3 Gen Preview vs StepAudio 3 Realtime PreviewComparison planned — not yet published
- StepAudio 3 Gen Preview vs StepAudio 3 TTSComparison planned — not yet published
Fast Pivot — Access hundreds of AI models from a single API — competitive pricing, reliable uptime, enterprise-grade infrastructure.