feat(voice): Pas 2 — install voice deps, vendor discord-ext-voice-recv, setup assets

Foundation pentru Discord voice-to-voice pipeline.

- requirements.txt: faster-whisper, silero-vad, num2words, numpy, PyNaCl
- vendor/discord-ext-voice-recv/: vendored la commit ac04ea7b09 (bump version
  0.5.3a) — Discord voice protocol fragil, upstream hobby fork. Adapter layer
  in src/voice/_discord_voice_adapter.py izolează churn (swap la py-cord =
  doar acel fișier rescris). VENDOR_INFO.md documentează update procedure.
- tools/voice_setup.py: idempotent setup script — libopus check, ffmpeg
  check, Supertonic reachable, faster-whisper/silero-vad warm, assets
  generation. Exit 0 = green, 1 = needs human (currently libopus missing
  needs `sudo apt install -y libopus0`).
- assets/voice/: thinking.wav (filler "Stai puțin să-mi adun gândurile",
  ~2.8s), mhm.wav (listener noise), beep_200ms.wav (wake-up tone 880Hz).
- src/voice/__init__.py: package stub.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

requirements.txt

@@ -7,3 +7,14 @@ httpx>=0.27
 pytest>=8.0
 supertonic[serve]>=1.3.1
 trafilatura>=1.8
+
+# Voice pipeline (Pas 2 setup)
+faster-whisper>=1.0
+silero-vad>=5.1
+num2words>=0.5
+numpy>=1.24
+PyNaCl>=1.5
+# discord-ext-voice-recv vendored at vendor/discord-ext-voice-recv/
+#   pinned commit: ac04ea7b0941112e83767cf1c1469b408fa06748
+#   install: pip install -e vendor/discord-ext-voice-recv
+# System deps (NOT pip): libopus0 (apt), ffmpeg