Tortoise TTS is an open-source text-to-speech program that generates highly realistic speech. It offers multi-voice capabilities with customizable voices and gives precise control over prosody and intonation. To use Tortoise TTS, you’ll need an NVIDIA GPU, then you can install via pip or Docker. Please follow the installation instructions on the GitHub page depending on your local setup. It provides multiple interfaces from command line scripts to API access for programmatic use. There is also a Hugging Face demo available where you can freely test some of the voices. Tortoise TTS is licensed under Apache 2.0 and completely free to use.
