WhisperSpeech
An open-source text-to-speech system that generates English audio with downloadable models and runs locally or in Google Colab.
WhisperSpeech is a text-to-speech system for developers and speech researchers who want to generate English audio with models they can run locally. It builds on OpenAI Whisper and provides pretrained models for use on your own hardware.
The available models use LibreLight training data. The project also provides converted datasets for research and development, and states that its models use properly licensed training data. You can run the notebooks locally or use Google Colab, where the workload runs in the cloud. The repository is open source under the MIT license.
Logotyper
