---
title: "Create Transcription"
method: POST
path: "/v1/audio/transcriptions"
tags: ["audio"]
---

# Create Transcription

`POST /v1/audio/transcriptions`

## Request

- Base URL: `https://api.oxlo.ai` (the document declares no server; this is the origin it was published from)
- URL: `https://api.oxlo.ai/v1/audio/transcriptions`
- Auth: HTTP bearer

Transcribe audio to text using Whisper.

OpenAI-compatible endpoint for speech-to-text.
Supports mp3, mpeg, mpga, m4a, wav, webm, ogg, and flac formats.
Maximum file size: 25 MB.

## Request body `multipart/form-data`

- BodyCreateTranscriptionV1AudioTranscriptionsPost
  - `file` string, binary, required: Audio file to transcribe
  - `model` string: Whisper model to use
  - `language` string, nullable: Language code (auto-detect if not provided)
  - `response_format` string: Response format: json, text, verbose_json

## Response `200`

Successful Response

- unknown

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/oxlo/apis/oxlo-backend.md) - [All operations](https://skmtc.dev/oxlo/apis/oxlo-backend/llms.txt) - [OpenAPI document](https://skmtc.dev/oxlo/apis/oxlo-backend/revisions/bc2ecdc94f31?raw)