Skip to navigation

StepAudio 2.5 ASR

StepAudio 2.5 ASR
StepFun · Transcription
POST /v1/audio/transcriptions

StepFun streaming speech recognition model for Chinese and English audio transcription.

See StepAudio 2.5 ASR pricing and specs or try it in the Playground.

At a glance

FieldValue
Model idstepaudio-2-5-asr
Model release date2026-04-24
Input modalitiesAudio
Output modalitiesText
Context window-
Weight precision-
RegionInternational
Featurestranscription, speech_to_text, streaming_asr, timestamps
Native inferenceNo
NewNo
Supported endpointsPOST /v1/audio/transcriptions
Alternate model idsstepaudio-2.5-asr, stepfun/stepaudio-2-5-asr, stepfun/stepaudio-2.5-asr

Pricing

ChargeSpecRate
Transcriptionper hour of audio$0.05

Example request

curl https://api.empiriolabs.ai/v1/audio/transcriptions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-F model=stepaudio-2-5-asr \
-F file=@meeting.mp3

Parameters

ParameterTypeRequiredDefaultDescription
fileaudiono-Audio file upload for transcription.
file_urlstringno-Public URL to an audio file.
audio_base64stringno-Base64 audio payload for JSON requests.
languageenumno"en"Recognition language. · Allowed: en, zh
hotwordsarrayno-Optional hotword list.
enable_itnbooleannotrueEnable inverse text normalization, which writes numbers, dates, and currency in their written form.
formatenumno-Audio container format. When omitted, it is detected from the uploaded file. · Allowed: wav, mp3, ogg, pcm
codecstringno-PCM codec such as pcm_s16le.
rateintegerno16000PCM sample rate in Hz. · Range: 8000 – 48000
bitsintegerno16PCM bit depth. · Range: 8 – 32
channelintegerno1PCM channel count. · Range: 1 – 8

Notes

Supports wav, mp3, ogg, and pcm input. PCM requests should include codec, sample rate, bit depth, and channel count. Recognition language supports Chinese and English. Timestamp output is available through enable_timestamp.


Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/stepaudio-2-5-asr.