whisper-1

Brief: Transcribe audio to text using OpenAI whisper-1.

---

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, or webm. Max file size 25 MB
model	string	Yes	Model name, set to whisper-1
prompt	string	No	Optional prompt text to guide transcription style. Should match the audio language
response_format	string	No	Output format. Supported: json, text, srt, verbose_json, vtt. Default: json
temperature	number	No	Sampling temperature, range 0 to 1. Higher values increase randomness, lower values increase stability
timestamp_granularities	array	No	Timestamp granularity. Options: response_format, verbose_json, word, segment
language	string	No	Audio language. Use ISO-639-1 codes to improve transcription accuracy

---

curl Example

curl -X POST "https://api.gpt.ge/v1/audio/transcriptions" \
  -H "Authorization: Bearer sk-xxxx" \
  -F "file=@./audio.wav" \
  -F "model=whisper-1" \
  -F "response_format=json" \
  -F "language=zh"

JavaScript (fetch) Example

const formData = new FormData();
formData.append('file', audioFile);
formData.append('model', 'whisper-1');
formData.append('response_format', 'json');
formData.append('language', 'zh');

fetch('https://api.gpt.ge/v1/audio/transcriptions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer sk-xxxx'
  },
  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-1',
        'response_format': 'json',
        'language': 'zh'
    }
    response = requests.post(
        'https://api.gpt.ge/v1/audio/transcriptions',
        headers={'Authorization': 'Bearer sk-xxxx'},
        files=files,
        data=data
    )
print(response.json())

---

Response Example (200)

{
  "text": "Hello, I am OpenAI Whisper."
}

Note: If response_format is srt, vtt, or verbose_json, the output will include detailed timestamps or subtitle information.