Speech-to-Text Transcription Streaming Multilingual

import asyncio
import json
import aiohttp

API_KEY = "YOUR_API_KEY"
AUDIO_FILE = "recording.opus"
CHUNK_SIZE = 8192

async def transcribe_streaming():
    url = (
        f"wss://platform.modulate.ai/api/velma-2-stt-streaming"
        f"?api_key={API_KEY}"
        f"&speaker_diarization=true"
        f"&emotion_signal=true"
        f"&accent_signal=true"
    )

    utterances = []

    async with aiohttp.ClientSession() as session:
        async with session.ws_connect(url) as ws:

            async def send_audio():
                with open(AUDIO_FILE, "rb") as f:
                    while chunk := f.read(CHUNK_SIZE):
                        await ws.send_bytes(chunk)
                        await asyncio.sleep(CHUNK_SIZE / 4000)
                await ws.send_str("")

            send_task = asyncio.create_task(send_audio())

            try:
                async for msg in ws:
                    if msg.type == aiohttp.WSMsgType.TEXT:
                        data = json.loads(msg.data)
                        if data["type"] == "utterance":
                            u = data["utterance"]
                            utterances.append(u)
                            print(f"[Speaker {u['speaker']}] {u['text']}")
                        elif data["type"] == "done":
                            print(f"Done. Duration: {data['duration_ms']}ms")
                            break
                        elif data["type"] == "error":
                            print(f"Error: {data['error']}")
                            break
                    elif msg.type in (
                        aiohttp.WSMsgType.ERROR,
                        aiohttp.WSMsgType.CLOSE,
                        aiohttp.WSMsgType.CLOSED,
                    ):
                        break
            finally:
                if not send_task.done():
                    send_task.cancel()

    full_text = " ".join(u["text"] for u in utterances)
    print(f"\nFull transcript:\n{full_text}")

asyncio.run(transcribe_streaming())