Quickstart

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

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

async def send_audio(ws, path):
    # 24 kHz mono PCM16, then 5 s of silence while the model answers.
    with wave.open(path, "rb") as f:
        assert f.getframerate() == 24000 and f.getsampwidth() == 2
        assert f.getnchannels() == 1
        audio = f.readframes(f.getnframes()) + bytes(48000 * 5)
    # 3,840 bytes at a time, paced against a clock at the speed of speech.
    started = time.monotonic()
    for offset in range(0, len(audio), 3840):
        await ws.send(json.dumps({
            "type": "session.input_audio.append",
            "audio": base64.b64encode(audio[offset:offset + 3840]).decode(),
        }))
        await asyncio.sleep(max(0, started + (offset + 3840) / 48000 - time.monotonic()))
    await ws.send(json.dumps({"type": "session.close"}))

async def main():
    async with websockets.connect(URL, additional_headers=HEADERS) as ws:
        # session.start must be the first event, or the socket refuses it.
        await ws.send(json.dumps({
            "type": "session.start",
            "session": {"model": "nemotron-voicechat"},
        }))
        sender = asyncio.create_task(send_audio(ws, "speech-24000-mono.wav"))

        reply = bytearray()
        async for raw in ws:
            event = json.loads(raw)
            kind = event.get("type", "")
            if kind == "session.output_audio.delta":
                reply += base64.b64decode(event["delta"])
            elif kind.endswith("_transcript.delta"):  # both sides' transcripts
                print(event.get("delta", ""), end="", flush=True)
            elif kind in ("session.closed", "error"):
                break
        sender.cancel()

    with wave.open("reply.wav", "wb") as f:
        f.setnchannels(1); f.setsampwidth(2); f.setframerate(24000)
        f.writeframes(bytes(reply))

asyncio.run(main())

import asyncio, base64, os, time, wave
from openai import AsyncOpenAI

client = AsyncOpenAI(
    api_key=os.environ["DOTWAVE_API_KEY"],
    base_url="https://api.dotwave.ai/v1",
)

async def send_wav(conn, 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
            audio = base64.b64encode(chunk).decode()
            await conn.input_audio_buffer.append(audio=audio)
            sent += len(chunk) // 2
            await asyncio.sleep(max(0, started + sent / 24000 - time.monotonic()))

async def print_transcripts(conn):
    async for event in conn:
        if event.type == "conversation.item.input_audio_transcription.delta":
            print(event.delta, end="", flush=True)
        elif event.type == "conversation.item.input_audio_transcription.completed":
            print()

async def main():
    async with client.realtime.connect(model="nemotron-asr-streaming") as conn:
        await conn.session.update(session={
            "type": "transcription",
            "audio": {"input": {
                "format": {"type": "audio/pcm", "rate": 24000},
                "transcription": {
                    "model": "nemotron-asr-streaming",
                    "language": "pt-BR",
                },
            }},
        })
        printer = asyncio.create_task(print_transcripts(conn))
        await send_wav(conn, "fala-24k.wav")
        await asyncio.sleep(4)  # the last segment completes after 3.2 s of silence
        printer.cancel()

asyncio.run(main())

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

URL = ("wss://api.dotwave.ai/v1/listen"
       "?encoding=linear16&sample_rate=24000&language=pt-BR")
HEADERS = {"Authorization": f"Token {os.environ['DOTWAVE_API_KEY']}"}

async def send_wav(ws, path):
    # 24 kHz mono PCM16 as binary messages, paced 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(chunk)
            sent += len(chunk) // 2
            await asyncio.sleep(max(0, started + sent / 24000 - time.monotonic()))
    # Send what is still open as a final, then close.
    await ws.send(json.dumps({"type": "CloseStream"}))

async def main():
    async with websockets.connect(URL, additional_headers=HEADERS) as ws:
        sender = asyncio.create_task(send_wav(ws, "fala-24k.wav"))
        async for raw in ws:
            message = json.loads(raw)
            if message.get("type") == "Results" and message["is_final"]:
                print(message["channel"]["alternatives"][0]["transcript"])
        await sender

asyncio.run(main())