feat: add Groq STT support and fix voice mode keybinding

- Add multi-provider STT support (OpenAI > Groq fallback) in transcription_tools
- Auto-correct model selection when provider doesn't support the configured model
- Change voice record key from Ctrl+Space to Ctrl+R (macOS compatibility)
- Fix duplicate transcript echo in voice pipeline
- Add GROQ_API_KEY to .env.example

hermes_cli/config.py

@@ -204,7 +204,7 @@ DEFAULT_CONFIG = {
     },
 
     "voice": {
-        "record_key": "ctrl+space",
+        "record_key": "ctrl+r",
         "max_recording_seconds": 120,
         "auto_tts": False,
     },