---
title: "Transcribe an audio file"
method: POST
path: "/v1/audio/transcriptions"
tags: ["Transcription"]
---

# Transcribe an audio file

`POST /v1/audio/transcriptions`

Upload an audio file with multipart/form-data and receive an OpenAI-compatible transcript response. Set response_format=verbose_json to include segments and timing metadata.

## Response `200`

Transcription result

- union
  - TranscriptionTextResponse
    - `text` string, required — Cleaned transcript text.
  - VerboseTranscriptionResponse
    - `text` string, required
    - `segments` TranscriptionSegment[], required
      - `start` number, float, required — Segment start time in seconds.
      - `end` number, float, required — Segment end time in seconds.
      - `text` string, required
      - `speaker` string, nullable — Speaker label when available.
    - `language` string, required
    - `duration` number, float, required — Server-side transcription latency in seconds.
    - `model` string, required

## Other responses

- `400` — Unknown model alias
- `422` — Invalid multipart request
- `500` — Transcription runtime error

---

[API](https://skmtc.dev/modelscope/apis/funasr-openai-compatible-api.md) · [All operations](https://skmtc.dev/modelscope/apis/funasr-openai-compatible-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/modelscope/funasr-openai-compatible-api/revisions/48c5cbd44749/schema)