LLM Reference

StepAudio 2.5 ASR

step-audio-2-5-asr

Researched today

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

ProprietaryMultimodalVision

StepAudio 2.5 ASR is worth evaluating for vision when its provider route and context window match the workload.

Decision context: Vision task fit, 1 tracked provider route, and research from 2026-05-27.

Use it for

  • Teams evaluating vision
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Strict JSON or tool-calling flows

Cheapest output

-

StepFun per 1M tokens

Provider routes

1

Tracked API hosts

Quality / dollar

Unknown

No task benchmark coverage yet

Freshness

2026-05-27

Researched today

fresh

Top use-case fit

Vision

Included by capability and metadata signals in the decision map.

Provider price ladder

ProviderInput / 1MOutput / 1MRoute
StepFun--
ServerlessPartial

Benchmark peer barsfor Vision

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

About

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.

Capabilities

MultimodalAudio

Rankings

Specifications

Released2026-05-22
Parameters4B
Specializationspeech-recognition
LicenseProprietary
Fine-tuning0

Created by

One of China's leading AI 'Six Tigers'.

Shanghai, China
Founded 2023
Website

Providers(1)