AI Model Radar
中文 EN

StepAudio 2.5 Realtime

StepFun
Model overview

stepaudio-2.5-realtime

StepFun's bidirectional realtime audio model available through the China-region Step Plan.

speechaudiorealtimemultimodalrealtime voicevoice assistantenterprise access
CompareCompanyRankingsPublic signals
Representative version

stepaudio-2.5-realtime

CompanyStepFun
ReleaseNot disclosed
Release typeModel release
ParametersNot disclosed
ArchitectureNot disclosed
ContextNot disclosed
Input modalitiesaudio / text
Output modalitiesaudio / text
Tool use / function callingNot disclosed
Structured output / reasoningNot disclosed
Vision / audio / videoConfirmed: Audio
Open weights / LicenseNo open weights / license not applicable
stepfun-stepaudio-2-5-realtime-current · License not applicable
Vendor APIAvailable
StepFun China audio APIstepfun-stepaudio-2-5-realtime-current · 2026-07-13
OpenRouterNot separately listed on OpenRouter
PricingNo reliable public source
BenchmarkNo reliable public source
Public signalsNo reliable public source
Use casesRealtime voice agents / Spoken dialogue / Interactive audio / realtime voice
Claim evidenceRelease / model specs / weightsStepFun China audio APIstepaudio-2.5-realtime
OpenRouter

Pricing / context / availability

OpenRouterNot separately listed on OpenRouter
OpenRouter listingNot separately listed in the current OpenRouter public list
Mapped versionstepaudio-2.5-realtime
stepfun-stepaudio-2-5-realtime-current
PricingNo reliable public source
ContextNot disclosed
Speed/LatencyNo reliable public source
Snapshot time2026-07-15T20:11:41.551Z
SourceView source
Evidence gaps

Public display boundary

Parameter scale not disclosedRelease date not disclosedOpenRouter not separately verifiedNo reliable benchmark sourceNo public model-card activity countersNo linkable real reviewSpeed/latency not disclosed