AudioSlicer Pro API

REST API documentation for integrating with our audio processing services

Endpoints

Authentication

X-API-KEY: your_api_key
POST

/api/transcribe

Transcribe audio files using Whisper v3 or DeepSeek Speech models.

Parameters

{
  "audio": "base64_encoded_audio",
  "model": "whisper|deepseek|auto",
  "language": "auto|en|es|fr|de|...",
  "timestamps": true,
  "speakers": false
}

Example Response

{
  "success": true,
  "processing_time": 4.32,
  "segments": [
    {
      "start": 0.0,
      "end": 5.24,
      "text": "Hello world...",
      "speaker": "Speaker 1"
    }
  ]
}
POST

/api/segment

Split audio files into logical segments based on silence detection.

GET

/api/analyze

Analyze audio characteristics and metadata.