# OpenAI Audio Transcription

OpenAI Audio Transcription

## Endpoint and authentication

`POST https://api.tu-zi.com/v1/audio/transcriptions`

Transport: multipart

Use an inference API key. Examples contain placeholders; read credentials from environment variables.

```http
Authorization: Bearer YOUR_API_KEY
```

## Body parameters

| Field | Type | Required | Description / constraints |
| --- | --- | --- | --- |
| model | string | Yes | Model identifier. |
| file | file | Yes | Audio file to transcribe. |
| language | string | No | Optional ISO-639-1 language code, for example zh or en. |
| response_format | string | No | Transcription output format. Form initial value (not an upstream default): "json" Values: "json", "text", "srt", "verbose_json", "vtt" |

## Minimal request example

```json
{
  "model": "YOUR_MODEL",
  "file": "@input.wav"
}
```

## Before running

Replace https://api.tu-zi.com with this site origin (do not append /v1 twice), and YOUR_MODEL with the exact marketplace model ID. Install requests for Python; use Node.js 20+ and save JavaScript as .mjs. WebSocket samples list their own dependencies.

Create an inference key on the site and set API_KEY in the environment; replace YOUR_API_KEY in cURL. Prepare local input.png/input.wav files for upload examples.

Start with a minimal request, then read the result using the response fields below. For async APIs, a returned task ID requires polling; acceptance does not mean generation has finished.

## Code examples

### curl

```bash
curl --request POST 'https://api.tu-zi.com/v1/audio/transcriptions' \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --form 'model=YOUR_MODEL' \
  --form 'file=@input.wav'
```

### python

```python
import json
import os
import requests

url = "https://api.tu-zi.com/v1/audio/transcriptions"
headers = json.loads("{\"Authorization\":\"Bearer YOUR_API_KEY\"}")
headers["Authorization"] = "Bearer " + os.environ["API_KEY"]
from contextlib import ExitStack
data = json.loads("{\"model\":\"YOUR_MODEL\"}")
with ExitStack() as stack:
    files = {}
    files["file"] = stack.enter_context(open("input.wav", "rb"))
    response = requests.request("POST", url, headers=headers, data=data, files=files, timeout=120)
response.raise_for_status()
result = response.json()
if isinstance(result, dict) and (result.get("success") is False or result.get("error")):
    raise RuntimeError(json.dumps(result, ensure_ascii=False))
print(result)  # Also inspect protocol-specific status/code fields.
```

### javascript

```javascript
import { readFile } from 'node:fs/promises';
// Node.js 20+
const url = "https://api.tu-zi.com/v1/audio/transcriptions";
const headers = {
  "Authorization": "Bearer YOUR_API_KEY"
};
headers.Authorization = 'Bearer ' + process.env.API_KEY;
const body = new FormData();
body.append("model", "YOUR_MODEL");
body.append("file", new Blob([await readFile("input.wav")]), "input.wav");
const response = await fetch(url, { method: "POST", headers, body });
if (!response.ok) throw new Error(await response.text());
const result = await response.json();
if (result?.success === false || result?.error) throw new Error(JSON.stringify(result));
console.log(result); // Also inspect protocol-specific status/code fields.
```

## Response fields

| Field | Type | Description / constraints |
| --- | --- | --- |
| text | string | Transcript; response_format changes the representation. |

Illustrative response; some endpoints show essential fields only. Optional fields may be absent.

```json
{
  "text": "Hello"
}
```

## Errors and retries

Check HTTP status and protocol-specific errors; do not mix error formats across protocols. For 401/403 check credentials and permissions, for 429 back off, and for 5xx check gateway/upstream status. Error bodies may contain error/message/code depending on the protocol.

Use bounded exponential backoff for reads. Do not blindly retry task creation, generation, or key mutations, to avoid duplicate billing or execution.

## Constraints

This page describes the base protocol. Use the selected model quick start for supported fields, enums, limits and asynchronous behavior. Replace YOUR_MODEL. Form initial values are not upstream defaults.

## Documentation source

Definition version: 1

Reviewed: 2026-11-02

Source: https://api.tu-zi.com/en/docs/api/reference-relay-audio-transcription

Related protocol guide: https://api.tu-zi.com/docs/api/audio-realtime

This export contains documentation and examples only, without real credentials, account data or user requests.