WebSocket

import asyncio, base64, json, os, time, wave
import websockets

URL = "wss://api.dotwave.ai/v1/realtime"
HEADERS = {"Authorization": f"Bearer {os.environ['DOTWAVE_API_KEY']}"}

async def send_wav(ws, path):
    # 24 kHz mono PCM16, paced against a clock at the speed of speech.
    with wave.open(path, "rb") as wav:
        started, sent = time.monotonic(), 0
        while chunk := wav.readframes(1920):  # 1,920 samples at a time
            await ws.send(json.dumps({
                "type": "input_audio_buffer.append",
                "audio": base64.b64encode(chunk).decode(),
            }))
            sent += len(chunk) // 2
            await asyncio.sleep(max(0, started + sent / 24000 - time.monotonic()))

async def print_transcripts(ws):
    async for raw in ws:
        event = json.loads(raw)
        kind = event.get("type")
        if kind == "conversation.item.input_audio_transcription.delta":
            print(event["delta"], end="", flush=True)
        elif kind == "conversation.item.input_audio_transcription.completed":
            print(f"  [{event.get('audio_start_ms')}-{event.get('audio_end_ms')} ms]")
        elif kind == "error":
            print("\nerror:", event["error"]["message"])

async def main():
    async with websockets.connect(URL, additional_headers=HEADERS) as ws:
        await ws.send(json.dumps({
            "type": "session.update",
            "session": {
                "type": "transcription",
                "audio": {"input": {
                    "format": {"type": "audio/pcm", "rate": 24000},
                    "transcription": {
                        "model": "nemotron-asr-streaming",
                        "language": "pt-BR",
                    },
                    "turn_detection": {
                        "type": "server_vad",
                        "silence_duration_ms": 800,
                    },
                }},
            },
        }))
        receiver = asyncio.create_task(print_transcripts(ws))
        await send_wav(ws, "fala-24k.wav")
        await asyncio.sleep(2)  # the last segment completes after 800 ms of silence
        receiver.cancel()

asyncio.run(main())