---
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

---

[API](https://skmtc.net/keywordsai/apis/api-reference.md) · [All operations](https://skmtc.net/keywordsai/apis/api-reference/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/keywordsai/api-reference/revisions/4e064cf81dae/schema)