whisper-base

Brief: Transcribe audio to text using OpenAI whisper-base.

---

Overview

• Method: POST
• Path: /v1/audio/transcriptions
• Content-Type: multipart/form-data

Authentication

• Header: Authorization: Bearer <token>
• Supports bearer token authentication

---

Request Body Parameters

Parameter	Type	Required	Description
file	file	Yes	Audio file object, supporting flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm. Max file size 25 MB
model	string	Yes	Model name, set to whisper-base
language	string	No	Audio language. Supported values: zh, en, de, es. Use ISO-639-1 codes to improve accuracy

Optional Header: X-Failover-Enabled enables failover. If the current compute service is unavailable, the request may switch to a backup compute endpoint.

---

curl Example

curl -X POST "https://api.gpt.ge/v1/audio/transcriptions" \
  -H "Authorization: Bearer sk-xxxx" \
  -H "X-Failover-Enabled: true" \
  -F "file=@./audio.wav" \
  -F "model=whisper-base" \
  -F "language=zh"

JavaScript (fetch) Example

const formData = new FormData();
formData.append('file', audioFile);
formData.append('model', 'whisper-base');
formData.append('language', 'zh');

fetch('https://api.gpt.ge/v1/audio/transcriptions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer sk-xxxx',
    'X-Failover-Enabled': 'true'
  },
  body: formData
}).then(r => r.json()).then(console.log);

Python (requests) Example

import requests

with open('audio.wav', 'rb') as f:
    files = {'file': f}
    data = {
        'model': 'whisper-base',
        'language': 'zh'
    }
    response = requests.post(
        'https://api.gpt.ge/v1/audio/transcriptions',
        headers={
            'Authorization': 'Bearer sk-xxxx',
            'X-Failover-Enabled': 'true'
        },
        files=files,
        data=data
    )
print(response.json())

---

Response Example (200)

{
  "text": "Hello, this is OpenAI Whisper Base transcription."
}

Note: whisper-base is an open-source ASR model with faster processing speed, suitable for multi-language, accent, and noisy audio transcription.