Speech

Voice input and output settings for hands-free interaction with your agent.

Voice Input (STT)

Configure speech-to-text settings for voice input.

Features:

• Allow voice commands via microphone
• Select input language
• Choose transcription model quality
• Configure audio input device

Voice Output (TTS)

Configure text-to-speech settings for voice output.

Features:

• Read responses aloud using text-to-speech
• Adjust playback speed (1.0x default)with speech rate
• Select TTS providers

Whisper Settings

Configure OpenAI Whisper for transcription.

Model Selection:

Larger models are more accurate but slower. Choose based on your accuracy and performance needs.

GPU Acceleration:

Enable CUDA/GPU for faster transcription when hardware acceleration is available.

Fig 10.11