Skip to content
Model infoModelsSnapshot: 15 Oct 2026

StepFun / StepAudio

StepAudio 2.5 TTS

Speech synthesis with controllable delivery, streaming output and reference-audio voice cloning.

Speech & voice
availableClosed weightsText-to-speech
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
6 of 19 specification fields collected
Text input limit1,000 charactersSee specification notes below
LanguagesNot collectedAwaiting source review
Input billingSee ratesStepFun China
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum output
Not collected
Input modalities
Text, AudioSource for Input modalities (opens in a new tab)
Output modalities
AudioSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
Not collected
Maximum prompt characters
1,000 charactersSource for Maximum prompt characters (opens in a new tab)
Output formats
WAV, MP3, FLAC, Opus, PCMSource for Output formats (opens in a new tab)
Voice controls
Global instruction: at most 200 characters; inline parenthesized directions are not spoken.Source for Voice controls (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

StepFun China

Provider source (opens in a new tab)
API model ID
stepaudio-2.5-tts
Access
StepFun account and regional API key required. Documented availability, not a paid inference verification.
Regions
China platform (.com); deployment geography and data residency are not established by the hostname.
API endpoint URL
POST https://api.stepfun.com/v1/audio/speechSource for API endpoint URL (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Text-to-speechSpeech synthesis1CN¥5.8010,000 billing characters
Voice cloningVoice cloning add-on2CN¥9.90voice

Rate conditions

  1. One Chinese character = one billing character; two English letters or punctuation marks = one. Pay-as-you-go synthesis.
  2. Trial calls charge synthesis only. Successful production cloning is charged immediately. Separate from speech synthesis.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

StepFun China

Provider source (opens in a new tab)
API model ID
stepaudio-2.5-tts
Access
StepFun account and regional API key required. Documented availability, not a paid inference verification.
Regions
China platform (.com); deployment geography and data residency are not established by the hostname.
API endpoint URL
WSS wss://api.stepfun.com/v1/realtime/audioSource for API endpoint URL (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Text-to-speechSpeech synthesis1CN¥5.8010,000 billing characters
Voice cloningVoice cloning add-on2CN¥9.90voice

Rate conditions

  1. One Chinese character = one billing character; two English letters or punctuation marks = one. Pay-as-you-go synthesis.
  2. Trial calls charge synthesis only. Successful production cloning is charged immediately. Separate from speech synthesis.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

StepFun International

Provider source (opens in a new tab)
API model ID
stepaudio-2.5-tts
Access
StepFun account and regional API key required. Documented availability, not a paid inference verification.
Regions
International platform (.ai); deployment geography and data residency require account-specific confirmation.
API endpoint URL
POST https://api.stepfun.ai/v1/audio/speechSource for API endpoint URL (opens in a new tab)
Languages
Chinese, English, Japanese (preview), Korean (preview), French (preview), Spanish (preview)Source for Languages (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Text-to-speechSpeech synthesis1$0.8510,000 billing characters
Voice cloningVoice cloning add-on2$1.50voice

Rate conditions

  1. One Chinese character = one billing character; two English letters or punctuation marks = one. Pay-as-you-go synthesis.
  2. Trial calls charge synthesis only. Successful production cloning is charged immediately. Separate from speech synthesis.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

StepFun International

Provider source (opens in a new tab)
API model ID
stepaudio-2.5-tts
Access
StepFun account and regional API key required. Documented availability, not a paid inference verification.
Regions
International platform (.ai); deployment geography and data residency require account-specific confirmation.
API endpoint URL
WSS wss://api.stepfun.ai/v1/realtime/audioSource for API endpoint URL (opens in a new tab)
Languages
Chinese, English, Japanese (preview), Korean (preview), French (preview), Spanish (preview)Source for Languages (opens in a new tab)
Provider quality guidance
Provider warns WebSocket quality may be significantly lower than HTTP synthesis; prefer HTTP when latency is not critical.Source for Provider quality guidance (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Text-to-speechSpeech synthesis1$0.8510,000 billing characters
Voice cloningVoice cloning add-on2$1.50voice

Rate conditions

  1. One Chinese character = one billing character; two English letters or punctuation marks = one. Pay-as-you-go synthesis.
  2. Trial calls charge synthesis only. Successful production cloning is charged immediately. Separate from speech synthesis.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

StepFun China

stepaudio-2.5-tts
Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

StepFun China

stepaudio-2.5-tts
Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

StepFun International

stepaudio-2.5-tts
Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

StepFun International

stepaudio-2.5-tts
Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Voice choices

31 voices

Choose a voice within StepAudio 2.5 TTS. These are API voice identifiers, not additional model releases. Source links document each voice.

Published voice catalog
Voice / API IDLanguage & accentDelivery
活力轻快livelybreezy-femaleNot specifiedOfficial recommended voice in the China TTS guide; this is a published selection, not a complete authenticated voice inventory.Voice source (opens in a new tab)
正派青年zhengpaiqingnianNot specifiedOfficial recommended voice in the China TTS guide; this is a published selection, not a complete authenticated voice inventory.Voice source (opens in a new tab)
爽快男声shuangkuainanshengNot specifiedOfficial recommended voice in the China TTS guide; this is a published selection, not a complete authenticated voice inventory.Voice source (opens in a new tab)
干练女声ganliannvshengNot specifiedOfficial recommended voice in the China TTS guide; this is a published selection, not a complete authenticated voice inventory.Voice source (opens in a new tab)
亲和女声qinhenvshengNot specifiedOfficial recommended voice in the China TTS guide; this is a published selection, not a complete authenticated voice inventory.Voice source (opens in a new tab)
活力女声huolinvshengNot specifiedOfficial recommended voice in the China TTS guide; this is a published selection, not a complete authenticated voice inventory.Voice source (opens in a new tab)
气质温婉elegantgentle-femaleNot specifiedOfficial recommended voice in the China TTS guide; this is a published selection, not a complete authenticated voice inventory.Voice source (opens in a new tab)
温柔男声wenrounanshengNot specifiedOfficial recommended voice in the China TTS guide; this is a published selection, not a complete authenticated voice inventory.Voice source (opens in a new tab)

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Inferred for this named native commercial service from official model/API documentation and comparison with StepFun’s public model repositories. No release of weights for this exact named service was found in the reviewed inventory. Public Step 3/3.5/3.7, Step-Audio Mini/R1/R1.1, Step1X and StepVideo releases are excluded; this does not assert that every StepFun model is closed.

Classification evidence (opens in a new tab)

Sources reviewed