News for hackers. Stuff that matters.

A comment on StyleTTS2 – open-source Eleven Labs quality Text To Speech. Parent comment

Re:StyleTTS2 – open-source Eleven Labs quality Text To Speech by nmfisher on Sunday November 19, 2023 @07:04PM (#38340132)
I think you’re talking about just using Whisper to annotate audio for a TTS pipeline but someone from Collabora actually created a TTS model directly from Whisper embeddings https://github.com/collabora/WhisperSpeech
[ Parent | on HN ]

There are no comments on this comment yet.