/v1/audio/speech

Every StepAudio model on EmpirioLabs AI, 11 in all. Compare them, then call the one that fits your task, quality, and pricing needs.
StepAudio on EmpirioLabs brings together 11 model APIs from StepFun, including StepAudio 3 TTS, StepAudio 3 Chat, StepAudio 3 Gen, StepAudio 3 Music. Each model keeps its own dedicated page with live pricing, parameters, docs, and playground access.
Compare the family at a glance, then open a model page for the complete live rate card and parameters.
Audio Generation: Priced by characters of text
| Model | Lowest rate | Applies to |
|---|---|---|
| StepAudio 3 Gen | $0.14 per 10,000 characters | Generation |
| StepAudio 3 TTS | $0.14 per 10,000 characters | Synthesis |
| StepAudio 2.5 TTS | $0.85 per 10,000 characters | Synthesis |
Text Generation: Per 1M tokens, by input rate
| Model | Input | Output |
|---|---|---|
| StepAudio 2.5 Chat | $1.50 | $3.50 |
| StepAudio 3 Chat | $1.50 | $3.50 |
Transcription: Priced per minute or hour of audio
| Model | Lowest rate | Applies to |
|---|---|---|
| StepAudio 2.5 ASR | $0.05 per hour of audio | Transcription |
| StepAudio 2.5 ASR Stream | $0.40 per hour of audio | Transcription |
| StepAudio 3 ASR Max | $0.60 per hour of audio | Transcription |
/v1/audio/speech/v1/chat/completions/v1/audio/generations/v1/audio/generations/v1/audio/transcriptions/v1/realtime/v1/realtime/v1/realtime/v1/audio/transcriptions/v1/audio/speech/v1/chat/completionsOutputs from our published tests. Each one links to the post it comes from.
See prompt tests, output notes, and comparison runs that mention this model family.
Guides Qwen Audio 3.0 ASR vs Qwen Audio 3.1 ASR vs StepAudio 3 ASR Max vs Deepgram Nova-3: one voicemail We gave Qwen Audio 3.0 ASR, Qwen Audio 3.1 ASR, StepAudio 3 ASR Max and Deepgram Nova-3 the same voicemail with a name,...
Guides Qwen Audio 3.1 TTS Plus vs Qwen Audio 3.1 TTS vs Gemini 2.5 Pro TTS vs StepAudio 3 TTS: one narration We gave Qwen Audio 3.1 TTS Plus, Qwen Audio 3.1 TTS, Gemini 2.5 Pro TTS and StepAudio 3 TTS the same narration and...
Guides Qwen Audio 3.1 TTS Next vs StepAudio 3 Gen: one radio scene We gave Qwen Audio 3.1 TTS Next and StepAudio 3 Gen the same written radio scene, with two speakers, a sound effect and...StepAudio on EmpirioLabs covers 11 model APIs from StepFun: StepAudio 3 TTS, StepAudio 3 Chat, StepAudio 3 Gen, StepAudio 3 Music, StepAudio 3 ASR Max, StepAudio 3 Realtime, StepAudio 2.5 Realtime, StepAudio 2.5 ASR Stream, StepAudio 2.5 ASR, StepAudio 2.5 TTS, StepAudio 2.5 Chat. You use one EmpirioLabs API key and choose the model id that fits the request.
Start with the model whose dedicated page matches your speed, quality, and pricing needs, then test it in the EmpirioLabs playground. The comparison cards above link to each model's live rate card and quickstart.
Pay as you go, or choose a plan with weekly allowances. The cards on this page show a short live-catalog summary, and each model page shows the complete rate card that matches API billing.
StepAudio 3 Gen, StepAudio 3 TTS share the lowest rate per character of the 3 StepAudio models priced that way. The price table on this page shows each model's lowest rate and what it applies to.
Yes. Open any model page in this family and use its playground link to test prompts and parameters in the browser before integrating the API.
Check out our pricing or reach out if you want your own model deployed on our stack.