---
title: "Speech to text"
method: POST
path: "/api/audio/transcriptions"
tags: ["multimodal"]
---

# Speech to text

`POST /api/audio/transcriptions`

Transcribe audio to text through the Respan gateway with automatic logging.

## Headers

- `Authorization` string, required
- `X-Data-Respan-Params` string

## Response `200`

Transcription result.

- MultimodalSpeechToTextResponse200
  - `text` string — Transcribed text.
  - `language` string — Detected language.
  - `duration` number, double — Audio duration in seconds.
  - `words` ApiAudioTranscriptionsPostResponsesContentApplicationJsonSchemaWordsItems[] — Word-level timestamps (if requested).
    - `word` string
    - `start` number, double
    - `end` number, double
  - `segments` ApiAudioTranscriptionsPostResponsesContentApplicationJsonSchemaSegmentsItems[] — Segment-level timestamps (if requested).

## Other responses

- `401` — Unauthorized

## Changes

- **2026-08-13** `4e064cf81dae` — 8 info
  - added the new optional `header` request parameter `X-Data-Respan-Params`
  - added optional request body
  - added the non-success response with the status `401`
  - added the optional property `duration` to the response with the `200` status
  - …4 more
- **2026-07-31** `c26d550029f8` — 1 breaking, 6 warning, 1 info
  - removed the request body
  - deleted the `header` request parameter `X-Data-Respan-Params`
  - removed the optional property `duration` from the response with the `200` status
  - removed the optional property `language` from the response with the `200` status
  - …4 more

[Change history](https://skmtc.dev/keywordsai/apis/api-reference/changes/api/audio/transcriptions/post.md)

---

[API](https://skmtc.dev/keywordsai/apis/api-reference.md) · [All operations](https://skmtc.dev/keywordsai/apis/api-reference/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/keywordsai/api-reference/revisions/c61efaf24756/schema)