---
name: Stepaudio 2.5 Asr
slug: stepaudio-2-5-asr
type: Multimodal
providers:
  - stepfun
description: Speech transcription model for accurate audio-to-text and captioning workflows
tags:
  - step
  - multimodal
is_open_source: false
release_date: '2026-04-24'
capabilities:
  audio: true
  vision: false
  tool_use: false
  citations: false
  reasoning: false
---
Stepaudio 2.5 Asr is a Multimodal model.
Speech transcription model for accurate audio-to-text and captioning workflows