Test 1: record 5s from USB mic with RMS meter (PA_ALSA_PLUGHW for resampling)

tests/01-record-play/main.py

@@ -0,0 +1,85 @@
+#!/usr/bin/env python3
+"""Record 5s from the USB Speaker Phone with a live RMS meter, save out.wav.
+
+Pass criteria for the record stage:
+- Level meter visibly responds to speech and to silence.
+- out.wav is written and non-empty.
+"""
+import os
+os.environ.setdefault("PA_ALSA_PLUGHW", "1")
+
+import sys
+import time
+
+import numpy as np
+import sounddevice as sd
+import soundfile as sf
+
+SAMPLE_RATE = 16_000
+DURATION_S = 5
+CHANNELS = 1
+DTYPE = "int16"
+OUT_WAV = "out.wav"
+
+
+def find_usb_device() -> int:
+    for idx, dev in enumerate(sd.query_devices()):
+        name = dev["name"].lower()
+        if "usb" in name and dev["max_input_channels"] >= 1:
+            return idx
+    print("USB audio device not found. Devices:", file=sys.stderr)
+    print(sd.query_devices(), file=sys.stderr)
+    sys.exit(1)
+
+
+def rms(int16_buf: np.ndarray) -> float:
+    if int16_buf.size == 0:
+        return 0.0
+    x = int16_buf.astype(np.float32) / 32768.0
+    return float(np.sqrt((x * x).mean() + 1e-12))
+
+
+def record(device: int) -> np.ndarray:
+    print(f"Recording {DURATION_S}s from device {device} ({sd.query_devices(device)['name']!r})")
+    total_frames = SAMPLE_RATE * DURATION_S
+    buf = np.zeros((total_frames, CHANNELS), dtype=DTYPE)
+    frames_written = 0
+    start = time.monotonic()
+
+    def callback(indata, frames, time_info, status):
+        nonlocal frames_written
+        if status:
+            print(f"\n[status] {status}", file=sys.stderr)
+        end = min(frames_written + frames, total_frames)
+        buf[frames_written:end] = indata[: end - frames_written]
+        frames_written = end
+
+    with sd.InputStream(
+        samplerate=SAMPLE_RATE,
+        channels=CHANNELS,
+        dtype=DTYPE,
+        device=device,
+        blocksize=1024,
+        callback=callback,
+    ):
+        while frames_written < total_frames:
+            elapsed = time.monotonic() - start
+            tail = buf[max(0, frames_written - 1600) : frames_written]
+            level = rms(tail)
+            bar = "#" * int(level * 60)
+            print(f"\r{elapsed:4.1f}s |{bar:<60}|", end="", flush=True)
+            time.sleep(0.05)
+    print()
+    return buf
+
+
+def main() -> int:
+    device = find_usb_device()
+    audio = record(device)
+    sf.write(OUT_WAV, audio, SAMPLE_RATE)
+    print(f"Wrote {OUT_WAV} ({audio.shape[0]} frames @ {SAMPLE_RATE} Hz)")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())