Audio Requirements

// Capture mic audio at 16 kHz mono and stream it as pcm_s16le binary frames.
async function startMicrophone(ws) {
  const stream = await navigator.mediaDevices.getUserMedia({
    audio: {
      sampleRate: 16000,
      channelCount: 1,
      echoCancellation: true,
      noiseSuppression: true,
    },
  });
  const ctx = new AudioContext({ sampleRate: 16000 });
  const source = ctx.createMediaStreamSource(stream);
  const node = ctx.createScriptProcessor(2048, 1, 1); // ~128 ms per callback

  node.onaudioprocess = (e) => {
    const f32 = e.inputBuffer.getChannelData(0);
    const pcm = new Int16Array(f32.length);
    for (let i = 0; i < f32.length; i++) {
      pcm[i] = Math.max(-1, Math.min(1, f32[i])) * 0x7fff; // float32 -> int16
    }
    if (ws.readyState === WebSocket.OPEN) ws.send(pcm.buffer);
  };

  source.connect(node);
  node.connect(ctx.destination);
}

import asyncio
import numpy as np
import sounddevice as sd

async def stream_microphone(ws, sample_rate=16000, block_ms=40):
    """Capture 16 kHz mono audio and send it as pcm_s16le binary frames."""
    block = int(sample_rate * block_ms / 1000)
    loop = asyncio.get_running_loop()
    queue: asyncio.Queue = asyncio.Queue()

    def callback(indata, frames, time_info, status):
        pcm = (np.clip(indata[:, 0], -1.0, 1.0) * 32767).astype("<i2").tobytes()
        loop.call_soon_threadsafe(queue.put_nowait, pcm)

    with sd.InputStream(samplerate=sample_rate, channels=1,
                        dtype="float32", blocksize=block, callback=callback):
        while True:
            await ws.send(await queue.get())   # binary frame, ~40 ms of audio