feat(voice): real Discord listen+speak loop (STT->echo->TTS)

The bot (dave/bot.mjs) previously only joined the channel and counted audio
frames — it never fed STT or spoke back. Wire the real loop:

- Node bot: buffer each speaker's Opus->PCM utterance until AfterSilence,
  wrap as WAV, POST to the Python voice-turn endpoint, then play the returned
  reply wav into the channel via an AudioPlayer (ffmpeg->Opus). Skips its own
  audio, dedupes overlapping subscriptions, and ignores sub-0.35s noise.
- Python: new `python -m wsai --voice-server` serves /api/voice-turn — decode
  the uploaded utterance, GPU faster-whisper STT, produce a reply (echo of what
  was heard for now), GPU MeloTTS synth, return the reply wav (recognised/reply
  text ride along as X-Heard/X-Reply headers). Both engines pre-warmed; turns
  show in the dashboard feed. MeloTTS.synth() extracted for direct wav reuse.

Echo mode verifies listening+speaking+GPU recognition entirely in Discord; the
Claude brain is the next slice. Verified the endpoint round-trip: utterance wav
-> correct Korean X-Heard/X-Reply + a WAVE reply on device=cuda. 12 tests pass,
node --check clean.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

wsai/__main__.py

@@ -100,6 +100,47 @@ def _run_stt_test(host: str, port: int) -> None:
         dash.stop()
 
 
+def _run_voice_server(host: str, port: int) -> None:
+    """Serve the STT+TTS voice-turn endpoint that the Discord bot (dave/bot.mjs)
+    calls: it POSTs a captured utterance wav and gets back the reply wav to play
+    into the voice channel. Both STT and TTS run on the GPU and are pre-warmed.
+    The same page also shows the live turn feed. Echo mode for now (the reply is
+    what was heard); the Claude brain can be added as the next slice."""
+    import time
+
+    from .backends.melo import MeloTTS
+    from .backends.whisper import WhisperSTT
+    from .dashboard import Dashboard
+    from .monitor import Monitor
+
+    monitor = Monitor()
+    stt = WhisperSTT()
+    tts = MeloTTS()
+    dash = Dashboard(monitor, host=host, port=port, stt=stt, tts=tts)
+    dash.start()
+    monitor.set_components({"source": "none", "vision": "none", "stt": "whisper",
+                            "brain": "echo", "tts": "melo"})
+    monitor.set_status(running=True, listening=False)
+    monitor.log("info", "디스코드 음성 서버 시작 — STT+TTS GPU 워밍업 중…")
+    print("\n  STT+TTS 워밍업 중… (모델 로드 + CUDA 예열)")
+    dash.warm()
+    sdev = getattr(stt, "resolved_device", None) or "?"
+    monitor.set_status(listening=True)
+    monitor.log("info", f"음성 서버 준비 완료 (STT device={sdev}). 디스코드 봇 연결 대기.")
+
+    shown = host if host not in ("0.0.0.0", "") else _lan_ip()
+    print(f"\n  음성 서버 준비 완료 (STT device: {sdev})")
+    print(f"  대시보드/상태:   http://{shown}:{port}")
+    print(f"  봇 연결 엔드포인트: http://127.0.0.1:{port}/api/voice-turn\n")
+    try:
+        while True:
+            time.sleep(3600)
+    except KeyboardInterrupt:
+        pass
+    finally:
+        dash.stop()
+
+
 def main() -> None:
     ap = argparse.ArgumentParser(prog="wsai")
     ap.add_argument("--voice", action="store_true", help="eyes-free voice loop (STT -> Brain -> TTS)")
@@ -108,6 +149,8 @@ def main() -> None:
                     help="keep generating mock demo utterances forever (off by default)")
     ap.add_argument("--stt-test", action="store_true",
                     help="serve the dashboard with a live GPU STT recognition test")
+    ap.add_argument("--voice-server", action="store_true",
+                    help="serve STT+TTS voice-turn endpoint for the Discord bot (dave/bot.mjs)")
     ap.add_argument("--live", action="store_true", help="capture screen + Claude backends")
     ap.add_argument("--env", action="store_true", help="build from WSAI_* env vars")
     ap.add_argument("--port", type=int, default=int(os.environ.get("WSAI_DASHBOARD_PORT", "8787")),
@@ -126,6 +169,10 @@ def main() -> None:
         _run_stt_test(args.host, args.port)
         return
 
+    if args.voice_server:
+        _run_voice_server(args.host, args.port)
+        return
+
     if args.dashboard:
         # Default to the eyes-free voice preset for the demo; env can override.
         settings = Settings.from_env() if args.env else Settings.voice()