Speech to Text API – High-Accuracy Speech Recognition SDK

# Install: pip install requests
import requests

url = "https://yourvoic.com/api/v1/transcription/transcribe"
headers = {
    "X-API-Key": "YOUR_API_KEY"
}

files = {
    "file": ("recording.mp3", open("recording.mp3", "rb"), "audio/mpeg")
}

data = {
    "model": "cipher_max",  # Options: cipher_max, cipher_fast
    "language": "auto",           # Supports 'hi', 'ta', 'te', 'en-US' or 'auto' for Hinglish code-switching
    "response_format": "verbose_json",
    "timestamp_granularities": "word,segment",
    "prompt": "Medical transcription"
}

response = requests.post(url, headers=headers, files=files, data=data)

if response.status_code == 200:
    result = response.json()
    print("Transcript:", result["text"])
    print("Detected Language:", result.get("language"))
    for segment in result.get("segments", []):
        print(f"[{segment['start']}s -> {segment['end']}s] {segment.get('speaker', 'Speaker')}: {segment['text']}")
else:
    print(f"Error {response.status_code}: {response.text}")