Text‐to‐Speech - Capsize-Games/airunner GitHub Wiki

This page has moved

Text-to-Speech Features

Supported Models

  • SpeechT5: High-quality voice synthesis with support for multiple languages and accents. Ideal for natural-sounding speech applications.
  • eSpeak: Lightweight and fast text-to-speech engine. Suitable for systems with limited resources. Supports pitch, speed, and volume adjustments.
  • OpenVoice: Advanced voice cloning and text-to-speech library. Provides state-of-the-art performance for voice synthesis and cloning.

Advanced Settings

  • Voice Customization: Adjust pitch, speed, and volume.
  • Language Support: Includes multiple languages for text-to-speech conversion.
  • Model Selection: Choose between SpeechT5, eSpeak, and OpenVoice based on application requirements.