StepFun

StepAudio 2.5 ASR

CTX—

Speech to text

Input—

Output—

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

PaidProprietary894/1044

Drag to turn

StepFunTranscriptionPromo

StepAudio 2.5 ASR

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

stepaudio-2.5-asr

Type: Transcription
Quality: Not rated yet
Context window: —
Max output: —
Input price: —
Output price: —
Cache read: —
Cache write: —
Released: Apr 24, 2026
Knowledge cutoff: —
Takes in: Audio
Puts out: Text
Reasoning: No
Tool calling: No
Structured output: No
File attachments: No
Access: Paid
License: Proprietary
Rarity: Promo
Set number: 894/1044

Open StepFun docs Where to run it 2 Meet its creature Battle Audio8-ASR-Infinite

Weights aren’t public. Use is governed by StepFun’s terms. Specs from models.dev, last changed Oct 19, 2026. Official source: platform.stepfun.ai.

How good is it?

Public leaderboard scores for StepAudio 2.5 ASR, refreshed daily from Epoch AI and LMArena.

No public leaderboard lists StepAudio 2.5 ASR yet. Epoch AI and LMArena cover most chat, image, and video models from the big labs; embeddings, speech, and small open models mostly go unrated.

Where to run it

2 providers sell StepAudio 2.5 ASR through an API. Prices are per million tokens, cheapest first.

From the labStepFun (Global)— in · — out

API providers

Provider	Input	Output	Context
StepFun (China)`stepaudio-2.5-asr`	—	—	—
StepFun (Global)Official`stepaudio-2.5-asr`	—	—	—

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

StepAudio 2.5 ASR

StepAudio 2.5 ASR

How good is it?

Where to run it

API providers

More from StepFun

Step 5 Preview

Step 3.7 Flash

StepAudio 2.5 TTS

Step 3.5 Flash 2603

Step TTS 2

Step 3.5 Flash

Step 2 (16K)

Step 1 (32K)