---
title: "Speech to Text"
method: POST
path: "/v1/asr"
tags: ["OpenAPI v1"]
---

# Speech to Text

`POST /v1/asr`

## Request body

- object
  - `audio` string, binary, required — Audio to be converted to text
  - `language` string, nullable — Language to be used for the speech
  - `ignore_timestamps` boolean — Whether to return precise timestamps in the text, this will increase the latency in audio shorter than 30 seconds

## Response `200`

Request fulfilled, document follows

- object
  - `text` string, required
  - `duration` number, required — Duration of the audio in seconds
  - `segments` ASRSegment[], required
    - `text` string, required
    - `start` number, required
    - `end` number, required

## Other responses

- `401` — No permission -- see authorization schemes
- `402` — No payment -- see charging schemes
- `422`

---

[API](https://skmtc.dev/fish/apis/fishaudio-openapi.md) · [All operations](https://skmtc.dev/fish/apis/fishaudio-openapi/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/fish/fishaudio-openapi/revisions/bca9c1115c42/schema)