Python Speech to Text API Quickstart

# Step 1: Install requests library
# pip install requests

import requests
import json

# YourVoic API Endpoint & Key
API_URL = "https://yourvoic.com/api/v1/transcription/sync"
API_KEY = "YOURVOIC_API_KEY"  # Replace with key from yourvoic.com dashboard

def transcribe_audio(file_path):
    headers = {
        "Authorization": f"Bearer {API_KEY}"
    }
    
    # Optional metadata parameters
    data = {
        "model": "cipher_max",       # Options: "cipher_fast" or "cipher_max"
        "language": "hi",            # Language code: "hi", "en", "ta", "te", "auto"
        "response_format": "verbose_json", # Returns speaker diarization & timestamps
        "diarization": "true"
    }
    
    with open(file_path, "rb") as audio_file:
        files = {"file": audio_file}
        print("Sending audio to YourVoic Speech to Text API...")
        response = requests.post(API_URL, headers=headers, data=data, files=files)
    
    if response.status_code == 200:
        result = response.json()
        print("\n=== Transcription Result ===")
        print("Text:", result.get("text"))
        print("\n=== Speaker Diarization ===")
        for segment in result.get("segments", []):
            print(f"[{segment['start']:.2f}s - {segment['end']:.2f}s] {segment.get('speaker', 'Speaker')}: {segment['text']}")
        return result
    else:
        print(f"Error {response.status_code}: {response.text}")
        return None

if __name__ == "__main__":
    transcribe_audio("sample_recording.mp3")

# Step 1: Install asyncio & websockets
# pip install websockets asyncio

import asyncio
import websockets
import json

STREAM_URL = "wss://yourvoic.com/api/v1/transcription/stream"
API_KEY = "YOURVOIC_API_KEY"

async def stream_audio_from_microphone():
    headers = {
        "Authorization": f"Bearer {API_KEY}"
    }
    
    async with websockets.connect(STREAM_URL, extra_headers=headers) as websocket:
        print("Connected to YourVoic Real-Time WebSocket API!")
        
        # Task 1: Receive live partial transcripts
        async def receive_transcripts():
            async for message in websocket:
                data = json.loads(message)
                if data.get("type") == "partial":
                    print(f"⚡ Live Transcript: {data.get('text')}", end="\r")
                elif data.get("type") == "final":
                    print(f"\n✓ Final Segment: {data.get('text')}")

        # Task 2: Send PCM audio chunks (4KB frames)
        async def send_audio_chunks():
            with open("live_audio_stream.pcm", "rb") as pcm_file:
                while chunk := pcm_file.read(4096):
                    await websocket.send(chunk)
                    await asyncio.sleep(0.05)  # 50ms chunk interval
            await websocket.send(json.dumps({"type": "end_of_stream"}))

        await asyncio.gather(receive_transcripts(), send_audio_chunks())

if __name__ == "__main__":
    asyncio.run(stream_audio_from_microphone())