feat: add voice mode with push-to-talk and TTS output for CLI

Implements Issue #314 Phase 2 & 3:
- /voice command to toggle voice mode (on/off/tts/status)
- Ctrl+Space push-to-talk recording via sounddevice
- Whisper STT transcription via existing transcription_tools
- Optional TTS response playback via existing tts_tool
- Visual indicators in prompt (recording/transcribing/voice)
- 21 unit tests, all mocked (no real mic/API)
- Optional deps: sounddevice, numpy (pip install hermes-agent[voice])

hermes_cli/config.py

@@ -202,6 +202,12 @@ DEFAULT_CONFIG = {
             "model": "whisper-1",  # whisper-1, gpt-4o-mini-transcribe, gpt-4o-transcribe
         },
     },
+
+    "voice": {
+        "record_key": "ctrl+space",
+        "max_recording_seconds": 120,
+        "auto_tts": False,
+    },
     
     "human_delay": {
         "mode": "off",