---
title: "Create transcription"
method: POST
path: "/audio/transcriptions"
tags: ["Audio"]
---

# Create transcription

`POST /audio/transcriptions`

## Request

- Base URL: `https://app.freyavoice.ai/api/v2`
- URL: `https://app.freyavoice.ai/api/v2/audio/transcriptions`
- Auth: HTTP bearer

Transcribes an uploaded audio file using Freya's transcription models. (Closed Beta)

## Request body `multipart/form-data`

- object
  - `file` string, binary: Audio file to transcribe
  - `model` 'freya-transcribe-v1': Freya transcription model
  - `prompt` string, nullable: Optional context to guide the transcription
  - `response_format` 'json' | 'text' | 'srt' | 'verbose_json' | 'vtt'
  - `language` 'tr' | 'cs' | 'null', nullable: Language hint (supported: tr, cs)

## Response `200`

Transcription created

- object
  - `text` string, required: Full transcription text
  - `usage` object, required
    - `type` 'tokens', required: Usage accounting type
    - `input_tokens` number, required: Total input tokens
    - `input_token_details` object, required
      - `text_tokens` number, required: Text token count
      - `audio_tokens` number, required: Audio token count
    - `output_tokens` number, required: Output token count
    - `total_tokens` number, required: Sum of input and output tokens

## Other responses

- `400`: Validation error
- `401`: Missing or invalid token
- `500`: Server error

---

[API](https://skmtc.dev/freyavoice/apis/freyavoice-api.md) - [All operations](https://skmtc.dev/freyavoice/apis/freyavoice-api/llms.txt) - [OpenAPI document](https://skmtc.dev/freyavoice/apis/freyavoice-api/revisions/153d120f0c73?raw)