All AI models · LLM benchmarks · Methodology

StepAudio 2.5 ASR

Speech transcription model for accurate audio-to-text and captioning workflows

Model facts

Context window
not published tokens
Maximum output
not published tokens
Cheapest paid input
not published per 1M tokens
Cheapest paid output
not published per 1M tokens
Open weights
no
Providers
2

Capabilities and modalities

audio.

Observed price history

  • 2026-08-24: not published input / not published output per 1M tokens

API providers

  • StepFun (China) — model id stepaudio-2.5-asr; not published input / not published output per 1M tokens; provider documentation
  • StepFun (Global) — model id stepaudio-2.5-asr; not published input / not published output per 1M tokens; provider documentation