LLM Reference

StepAudio 2.5 ASR on StepFun

StepAudio 2.5 · StepFun

Serverless

Last refreshed 2026-05-27. Next refresh: weekly.

Why use StepAudio 2.5 ASR on StepFun?

StepFun offers StepAudio 2.5 ASR with competitive pricing. StepFun is a Chinese AI company providing API access to its Step series of large language and multimodal models.

Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: stepaudio-2.5-asr
Model ID
stepaudio-2.5-asr

Request example

Curated snippets for this provider are not sourced yet. Use StepFun documentation with model ID stepaudio-2.5-asr.

Gotchas

  • Use provider model ID "stepaudio-2.5-asr", not the LLMReference slug "step-audio-2-5-asr".

Capabilities

MultimodalAudio

About StepAudio 2.5 ASR

StepAudio 2.5 ASR is StepFun's automatic speech recognition model. At 4B parameters, it introduces Multi-Token Prediction (MTP) technology to parallelly predict multiple tokens per decoding step, enabling transcription of 5 minutes of audio in approximately 1 second. Achieves 400% higher throughput and 60% lower latency compared to prior StepFun ASR systems while maintaining state-of-the-art accuracy. Supports Chinese and English; accepts PCM, OGG, MP3, and WAV formats. Available via the StepFun API (model: stepaudio-2.5-asr). Part of the unified StepAudio 2.5 architecture described in arXiv:2605.23463.

FAQ

What API model ID do I use for StepAudio 2.5 ASR on StepFun?

Use the model ID stepaudio-2.5-asr when calling StepFun's API.

Who created StepAudio 2.5 ASR?

StepAudio 2.5 ASR was created by StepFun as part of the StepAudio 2.5 model family.

Is StepAudio 2.5 ASR open source?

StepAudio 2.5 ASR is not open source; the seed data lists it as proprietary.

Get Started

Model Specs

Released2026-05-22
Parameters4B