News for hackers. Stuff that matters.

A comment on ESpeak-ng: speech synthesizer with more than one hundred languages and accents. Parent comment

Re:ESpeak-ng: speech synthesizer with more than one hundred ... by Animats on Thursday May 02, 2024 @01:49AM (#40233087)
Most of the links there are dead.

That's a descendant of Festival Singer, which was well respected in its day.

What's a current practical text-to-speech system that's open source, local, and not huge?

[ Parent | on HN ]
Re:ESpeak-ng: speech synthesizer with more than one hundred ... by anthk on Thursday May 02, 2024 @04:00AM (#40233793)
Flite.
[ Parent | on HN ]
Re:ESpeak-ng: speech synthesizer with more than one hundred ... by Animats on Thursday May 02, 2024 @01:05PM (#40238569)
That's another spinoff of Festival Singer. What's good from the LLM era?
[ Parent | on HN ]
Re:ESpeak-ng: speech synthesizer with more than one hundred ... by follower on Thursday May 02, 2024 @03:23PM (#40240401)
Depending on your definition of "huge", you might find Piper TTS fits your requirements: https://github.com/rhasspy/piper

The size of the associated voice files varies but there are options that are under 100MB: https://huggingface.co/rhasspy/piper-voices/tree/main/en

[ Parent | on HN ]