E2-TTS is a fully non-autoregressive zero-shot text-to-speech model developed as part of the F5-TTS project. It is trained on the Emilia dataset and provides high-quality speech synthesis. The model can be used locally with provided checkpoints and is accompanied by a research paper detailing its embarrassingly easy approach to TTS.
E2 TTS sits in PulseGate's Voice, TTS & speech category. It focuses on generating natural speech from text in a zero-shot setting without complex autoregressive modeling. It is built as an open-source project for AI researchers and speech synthesis developers. E2 TTS is open source under the MIT license. The product ships for the web and API.
SWivid builds and maintains E2 TTS, and the product first shipped in 2024. Development happens publicly on GitHub with 15k stars and 5 commits in the last 90 days. Key capabilities include Zero-Shot TTS, non-Autoregressive, and F5-TTS Compatible.
Latest indexed changes and source events
SWivid/E2-TTS verified by the PulseGate indexer
Other apps tracked under the same category.
