The Voice Settings tab allows you to configure the text-to-speech (TTS) and speech-to-text (STT) capabilities of your AI agent.

​
Text to Speech

  • Voice Processor: Choose a TTS engine.
  • Voice Selection: Select a voice style (e.g., male, female, multilingual).
  • Language: Define the default language.
  • Phoneme Customization: Adjust phonemes for pronunciation fine-tuning.

​
Speech to Text

  • STT Processor: Choose a speech recognition model.
  • Boosted Keywords: Improve recognition of specific words.
  • Save Voice Recordings: Enable or disable recording storage.

​
Inactivity Settings

  • Hang-up Timeout: Define the time before call termination.
  • Reask Timeout: Set how long to wait before asking again.
  • Reask Phrases: Customize phrases for when the agent detects inactivity.

​
Environment Settings

  • Background Sound: Enable or disable environment sound during voice interactions.