TTS-Voice-Wizard VS silero-models

Maybe that? https://github.com/VRCWizard/TTS-Voice-Wizard

Hi, I'm in a similar boat and have been streaming for a little while. I will say that you should do what your most comfortable with. It will probably take time, but I think whatever you want to do work. I use a nice free Text to Speech called Voice Wizard if you decide you want that. Here's a link: https://github.com/VRCWizard/TTS-Voice-Wizard. I found it pretty easy to set up and there good options for more realistic voices.

you can use speech to text. i use this program for vrchat and it’s helped me socialize a lot more https://github.com/VRCWizard/TTS-Voice-Wizard

It does not tell me what program or anything is causing it, and I am unsure what to do. i am currently thinking about resetting my computer. I didn't download anything that would've caused it to my knowledge, only thing I can recount downloading was a program from Github: https://github.com/VRCWizard/TTS-Voice-Wizard which i don't think could have caused it.

Shouldn’t this still work? https://github.com/VRCWizard/TTS-Voice-Wizard

if you are mute irl then this won't help you but you can use https://github.com/VRCWizard/TTS-Voice-Wizard

I doubt it's currently actually "the best open source text to speech", but the answer I came up with when throwing a couple of hours at the problem some months ago was "Silero" [0, 1].

Following the "standalone" guide [2], it was pretty trivial to make the model render my sample text in about 100 English "voices" (many of which were similar to each other, and in varying quality). Sampling those, I got about 10 that were pretty "good". And maybe 6 that were the "best ones" (pretty natural, not annoying to listen to).

IIRC the license was free for noncommercial use only. I'm not sure exactly "how open source" they are, but it was simple to install the dependencies and write the basic Python to try it out; I had to write a for loop to try all the voices like I wanted. I ended using something else for the project for other reasons, but this could still be fairly good backup option for some use cases IMO.

  [0] https://github.com/snakers4/silero-models#text-to-speech

Glados was the first experiment. I moved on to silero afterwards: https://github.com/snakers4/silero-models

Some months ago I tried the Silero Models: https://github.com/snakers4/silero-models

With the audio sources I had, in English, the transcription had many mistakes. The good side is that installing and running the software worked as described in their documentation, so maybe it’s worth giving it a try by yourself.

Silero V3: fast high-quality text-to-speech in 20 languages with 173 voices\ (56 comments)