| # Phase 2 Voice Configuration | |
| # Copy relevant settings to your .env file | |
| # Enable Phase 2 voice features | |
| PHASE_2_ENABLED=true | |
| # Whisper ASR Configuration | |
| WHISPER_MODEL=base | |
| # Options: tiny, base, small, medium, large | |
| # Larger models = better accuracy but slower | |
| # Recommended: base for development, small/medium for production | |
| # TTS Configuration | |
| TTS_ENGINE=gtts | |
| # Options: gtts (Google TTS - free), indic_tts (future) | |
| # Voice Fraud Detection (Optional) | |
| VOICE_FRAUD_DETECTION=false | |
| # Set to true to enable synthetic voice detection | |
| # Requires additional dependencies (resemblyzer) | |
| # Audio Settings | |
| AUDIO_SAMPLE_RATE=16000 | |
| # Standard sample rate for speech recognition | |
| AUDIO_CHUNK_DURATION=5 | |
| # Duration in seconds for audio chunks in streaming mode | |
| # Performance Settings | |
| WHISPER_DEVICE=auto | |
| # Options: auto, cpu, cuda | |
| # auto = use GPU if available, else CPU | |