SenseVoiceSmall

Brief: Transcribe audio to text using the SenseVoiceSmall model, with multi-language automatic detection support.

---

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. Maximum file size is 25 MB
model	string	Yes	Model name, set to SenseVoiceSmall
language	string	No	Audio language. Supported values: auto, zh, en, de, es, yue, ja, ko, nospeech. Default: auto

Note: When language is set to auto, the model will automatically detect the audio language.

---

curl Example

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

JavaScript (fetch) Example

const formData = new FormData();
formData.append('file', audioFile);
formData.append('model', 'SenseVoiceSmall');
formData.append('language', 'auto');

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': 'SenseVoiceSmall',
        'language': 'auto'
    }
    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, this is the SenseVoiceSmall transcription result."
}

Note: SenseVoiceSmall supports multi-language recognition and automatic language detection, making it suitable for fast audio transcription.