REST API documentation for integrating with our audio processing services
Transcribe audio files using Whisper v3 or DeepSeek Speech models.
{
"audio": "base64_encoded_audio",
"model": "whisper|deepseek|auto",
"language": "auto|en|es|fr|de|...",
"timestamps": true,
"speakers": false
}
{
"success": true,
"processing_time": 4.32,
"segments": [
{
"start": 0.0,
"end": 5.24,
"text": "Hello world...",
"speaker": "Speaker 1"
}
]
}
Split audio files into logical segments based on silence detection.
Analyze audio characteristics and metadata.