---
title: "Transcribe audio"
description: "Transcribe audio to text. Drop-in replacement for OpenAI /v1/audio/transcriptions.\n\nAccepts multipart/form-data with an audio file. Supported models: whisper-1,\ngoogle/gemini-2.5-flash.\n\nAccepts tri-mode auth (user token / service+on-behalf-of / service-only) —\nthe service-key path is required for backend callers like BlinkLife that\nproxy STT on a user's behalf, mirroring /v1/audio/speech."
---

> Documentation Index
> Fetch the complete documentation index at: https://truememory-docs.mvstg.com/llms.txt
> Use this file to discover all available pages before exploring further.

Path: AI Gateway API › Chat

`POST /v1/audio/transcriptions`

Transcribe audio to text. Drop-in replacement for OpenAI /v1/audio/transcriptions.

Accepts multipart/form-data with an audio file. Supported models: whisper-1,
google/gemini-2.5-flash.

Accepts tri-mode auth (user token / service+on-behalf-of / service-only) —
the service-key path is required for backend callers like BlinkLife that
proxy STT on a user's behalf, mirroring /v1/audio/speech.

## Authentication

- `HTTPBearer`, http, header `Authorization`

## Header parameters

- `X-On-Behalf-Of` (`create_transcription.header.X-On-Behalf-Of`; any of, optional)
  - any of: `string`, `null`
- `X-External-User-Id` (`create_transcription.header.X-External-User-Id`; any of, optional)
  - any of: `string`, `null`
- `X-App-Id` (`create_transcription.header.X-App-Id`; any of, optional)
  - any of: `string`, `null`

## Request body

_Required._

- `file` (`create_transcription.file`; string, required)
- `model` (`create_transcription.model`; string, optional)
  - default `"whisper-1"`
- `language` (`create_transcription.language`; any of, optional)
  - any of: `string`, `null`
- `prompt` (`create_transcription.prompt`; any of, optional)
  - any of: `string`, `null`
- `response_format` (`create_transcription.response_format`; string, optional)
  - default `"json"`
- `temperature` (`create_transcription.temperature`; number, optional)
  - default `0`

## Example request

```text
{
  "file": "string",
  "model": "whisper-1",
  "language": "string",
  "prompt": "string",
  "response_format": "json",
  "temperature": 0
}
```

## Code samples

### cURL

```bash
curl --request POST \
  --url https://truememory-api.mvstg.com/v1/audio/transcriptions \
  --header 'Authorization: Bearer <token>' \
  --form-string 'file=string' \
  --form-string 'model=whisper-1' \
  --form-string 'language=string' \
  --form-string 'prompt=string' \
  --form-string 'response_format=json' \
  --form-string 'temperature=0'
```

### TypeScript

```typescript
const formData = new FormData();
formData.append('file', 'string');
formData.append('model', 'whisper-1');
formData.append('language', 'string');
formData.append('prompt', 'string');
formData.append('response_format', 'json');
formData.append('temperature', '0');

const url = 'https://truememory-api.mvstg.com/v1/audio/transcriptions';
const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}, body: formData};

fetch(url, options)
  .then(res => res.json())
  .then(json => console.log(json))
  .catch(err => console.error(err));
```

### Python

```python
import requests

url = "https://truememory-api.mvstg.com/v1/audio/transcriptions"

files = [
    ("file", (None, "string")),
    ("model", (None, "whisper-1")),
    ("language", (None, "string")),
    ("prompt", (None, "string")),
    ("response_format", (None, "json")),
    ("temperature", (None, "0"))
]
headers = {"Authorization": "Bearer <token>"}

response = requests.post(url, files=files, headers=headers)

print(response.text)
```

## Responses

### 200

The transcription. JSON by default; set `response_format` to `text`, `srt` or `vtt` for those formats instead.

#### Example

```json
{}
```

Any of:

- `object`
- `string`

### 422

Validation Error

#### Example

```json
{
  "detail": [
    {
      "loc": [
        "string"
      ],
      "msg": "string",
      "type": "string",
      "input": null,
      "ctx": {}
    }
  ]
}
```

- `detail` (`create_transcription.response.422.detail`; array<object>, optional)
  - `loc` (`create_transcription.response.422.detail.loc`; array<any of>, required)
    - any of: `string`, `integer`
  - `msg` (`create_transcription.response.422.detail.msg`; string, required)
  - `type` (`create_transcription.response.422.detail.type`; string, required)
  - `input` (`create_transcription.response.422.detail.input`; unknown, optional)
  - `ctx` (`create_transcription.response.422.detail.ctx`; object, optional)


Source: https://truememory-docs.mvstg.com/api/audio/transcriptions/index.md