NaturalSpeech: End-to-end text to speech synthesis with human-level quality

Re:NaturalSpeech: End-to-end text to speech synthesis with h... by DantesKite on Tuesday May 17, 2022 @09:39PM (#31418352)

That is crazy. Any way I can start using this soon? I have a backlog of articles I’d love to listen to.

[ Parent | on HN ]

Re:NaturalSpeech: End-to-end text to speech synthesis with h... by nwatab on Wednesday May 18, 2022 @09:02AM (#31422233)

Do you convert articles and listen to them?

[ Parent | on HN ]

Re:NaturalSpeech: End-to-end text to speech synthesis with h... by DantesKite on Wednesday May 18, 2022 @02:15PM (#31425892)

I do, but I don’t like many text to speech voices at the moment because they don’t always enunciate in a way that makes sense. So I’ve been looking forward to the day when I can use custom human voices to read me news articles.

[ Parent | on HN ]

Re:NaturalSpeech: End-to-end text to speech synthesis with h... by nwatab on Wednesday May 18, 2022 @10:14PM (#31429931)

I'm in the same boat. I have tried GCP and AWS, and they sound too robotic. Do you convert articles you wrote or random articles? The reason I'm asking is because I'm thinking about new project that works like Descript and that is much easy to use.

[ Parent | on HN ]

Re:NaturalSpeech: End-to-end text to speech synthesis with h... by VGltZUNvbnN1 on Wednesday May 18, 2022 @01:53AM (#31419643)

TortoiseTTS might be the closest https://github.com/neonbjb/tortoise-tts It's a few shot multi speaker model so you need just 3-4 little clips to train new voices.

[ Parent | on HN ]

Re:NaturalSpeech: End-to-end text to speech synthesis with h... by DantesKite on Wednesday May 18, 2022 @02:19AM (#31419772)

Thank you very much. This is what I was looking for.

[ Parent | on HN ]