feat: initial voice assistant implementation

5-state machine (LAUSCH/AUFNAHME/GENERATOR/VORLESE/DIALOG) with:
- Wake-word detection via openwakeword (hey_jarvis)
- Speech-to-text via faster-whisper large-v3 (GPU)
- LLM streaming via OpenAI-compatible backends (llama.cpp/ollama/openai)
- TTS via piper with automatic language detection and voice selection
- Selectable mic input (ReSpeaker, MOTU M2, camera, bluetooth, index)
- Selectable audio output sink
- Control words during playback (Stopp/Pause/Weiter/Noch einmal/…)
- "Stopp" abort in all active states → LAUSCH

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

transcribe.py

@@ -0,0 +1,115 @@
+#!/usr/bin/env python3
+"""
+Live-Transkription via faster-whisper (large-v3, GPU).
+
+Aufnahme-Logik:
+  - Puffert Audio in CHUNK_SEC-Sekunden-Blöcken
+  - Faster-whisper VAD filtert Stille heraus
+  - Ausgabe: fortlaufender Text auf stdout
+
+Verwendung:
+  python3 transcribe.py                           # ReSpeaker, GPU 2
+  python3 transcribe.py --mic motu                # MOTU M2
+  python3 transcribe.py --mic camera              # Kamera-Mikrofon
+  python3 transcribe.py --mic 17                  # sounddevice-Index direkt
+  python3 transcribe.py --list-mics               # alle Eingabegeräte anzeigen
+  python3 transcribe.py [--lang de] [--model large-v3] [--gpu 1]
+
+GPU-Belegung:
+  GPU 0  NVIDIA T600       (4 GB)   — reserviert
+  GPU 1  RTX 3090 (24 GB)           — llama.cpp / Port 8001
+  GPU 2  RTX 3090 (24 GB)           — Whisper (default)
+"""
+
+import argparse
+import queue
+import sys
+import numpy as np
+import sounddevice as sd
+from faster_whisper import WhisperModel
+from scipy.signal import resample_poly
+
+WHISPER_RATE = 16000
+CHUNK_SEC    = 5      # Sekunden pro Transkriptions-Durchlauf
+CHANNELS     = 1
+
+sys.path.insert(0, __import__("os").path.dirname(__file__))
+from mic import resolve_mic, print_mic_list, DEFAULT_MIC  # noqa: E402
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter
+    )
+    parser.add_argument("--mic",       default=DEFAULT_MIC,
+                        help="Eingabegerät: respeaker | motu | camera | default | "
+                             "bluetooth | <index> | <substring>")
+    parser.add_argument("--list-mics", action="store_true",
+                        help="Verfügbare Mikrofone anzeigen und beenden")
+    parser.add_argument("--lang",      default="de",       help="Sprache (de/en/…)")
+    parser.add_argument("--model",     default="large-v3", help="Whisper-Modell")
+    parser.add_argument("--gpu",       type=int, default=1,
+                        help="CUDA-Index innerhalb CUDA_VISIBLE_DEVICES (default: 1 = phys. GPU 2)")
+    args = parser.parse_args()
+
+    if args.list_mics:
+        print_mic_list()
+        return
+
+    device_idx, capture_rate, device_label = resolve_mic(args.mic)
+    chunk_samples = CHUNK_SEC * capture_rate
+
+    print(f"Mikrofon : {device_label} (Index {device_idx}, {capture_rate} Hz → resample → {WHISPER_RATE} Hz)")
+    print(f"Modell   : {args.model}  |  Sprache: {args.lang}  |  GPU: {args.gpu}")
+    print("Lade Modell …", flush=True)
+
+    model = WhisperModel(
+        args.model,
+        device="cuda",
+        device_index=args.gpu,
+        compute_type="float16",
+    )
+    print("Modell geladen. Spreche …\n", flush=True)
+
+    audio_q: "queue.Queue[np.ndarray]" = queue.Queue()
+
+    def callback(indata, frames, time_info, status):
+        if status:
+            print(f"[audio status] {status}", file=sys.stderr)
+        audio_q.put(indata[:, 0].copy())
+
+    try:
+        with sd.InputStream(
+            device=device_idx,
+            channels=CHANNELS,
+            samplerate=capture_rate,
+            dtype="float32",
+            blocksize=capture_rate // 4,  # 250 ms Blöcke
+            callback=callback,
+        ):
+            buffer = np.empty(0, dtype="float32")
+            while True:
+                while buffer.shape[0] < chunk_samples:
+                    buffer = np.concatenate([buffer, audio_q.get()])
+
+                chunk  = buffer[:chunk_samples].copy()
+                buffer = buffer[chunk_samples:]
+
+                chunk_16k = resample_poly(chunk, WHISPER_RATE, capture_rate)
+
+                segments, _ = model.transcribe(
+                    chunk_16k,
+                    language=args.lang,
+                    vad_filter=True,
+                    vad_parameters={"min_silence_duration_ms": 500},
+                    beam_size=5,
+                )
+                text = " ".join(s.text.strip() for s in segments).strip()
+                if text:
+                    print(text, flush=True)
+
+    except KeyboardInterrupt:
+        print("\nBeendet.")
+
+if __name__ == "__main__":
+    main()