StyleTTS 2 is a Hugging Face demo that synthesizes natural-sounding speech from any English text. Users can select from preset voices or upload a short audio sample to clone a custom voice. The generated audio can be played or downloaded directly.
StyleTTS 2 sits in PulseGate's Voice, TTS & speech category. It focuses on generating realistic spoken audio from text with customizable voices. StyleTTS 2 is a consumer product aimed at content creators and developers. StyleTTS 2 is free to use. It runs on the web, and it can be self-hosted.
StyleTTS builds and maintains StyleTTS 2, and it first shipped in 2023. Among its 3 catalogued features are text to speech, voice cloning, and preset voices.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do