StepAudio 2.5 TTS

ttsproprietary

Contextual text-to-speech with zero-shot voice cloning from 3 seconds of audio. Dual-layer prosody and emotion control.

Capabilities

No supported capabilities recorded.

Details

Model IDstepaudio-2.5-tts
Provider StepFun
Creator stepfun
Familystepaudio
Licenseproprietary
Statusactive
Typetts
Input modalitiesaudio, text
Output modalitiesspeech
Open weightYes
Parameters—
Architecture—
Max chars—
Sample rate—
Voices—
Languages—
Release date—
Sourceofficial

Endpoints

audio speechPOST
https://api.stepfun.com/audio-speech

Pricing

5.8 元／万字符 (CNY)

Family Comparison: stepaudio

ModelLanguages
StepAudio 2 ASR Pro—
StepAudio 2.5 ASR—
StepAudio 2.5 TTS—

API

GET/v1/models/stepfun/stepaudio-2.5-tts

StepAudio 2.5 TTS

stepaudio-2.5-tts

Contextual text-to-speech with zero-shot voice cloning from 3 seconds of audio. Dual-layer prosody and emotion control.

Changes · 5 entries
stepaudio-2.5-ttsupdateca7a400Nov 2, 2026, 03:02 AM
pricing_notes["0.85 USD per 10k characters (USD listed in english docs...→["5.8 元／万字符 (CNY)"]
taglineContextual text-to-speech with zero-shot voice cloning fr...
stepaudio-2.5-ttsupdateb2f45bfOct 29, 2026, 03:29 AM
statusdeprecated→active
pricing_notes["5.8 元/万字符 (CNY)."]→["5.8 元／万字符 (CNY)"]
stepaudio-2.5-ttsupdate40decdeSep 16, 2026, 06:38 AM
statusactive→deprecated
stepaudio-2.5-ttsupdatec67ed84Jul 31, 2026, 10:28 AM
pricing_notes["0.85 USD per 10k characters (USD listed in english docs...→["5.8 元/万字符 (CNY)."]
taglineContextual text-to-speech with zero-shot voice cloning fr...
stepaudio-2.5-ttscreate3e56cf1Apr 26, 2026, 07:23 PM