ttsprech

POST-EDIT, CORRECTED ANSWER 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 "ttsprech" [3]. Following the guide, 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" (very natural, not annoying to listen to, actually sounded like a person by and large), and maybe 2 made the top (as in, a tossup for the most listenable, all factors considered). 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

So, I've been playing with this a little bit now and here are some comments: - it is very fast and scales quite nicely on CPU with 4 threads (~ twice the speed), but not further (I tried it on a 64 cores box). Not sure why since they seem to be using torch's native threading support. - surprisingly, it is not that much faster when run on a GPU - the quality (as in: what I'm hearing, not a formally measured metric) is good but (YMMV) not as good as turtle. - it breaks with strange error messages if the text you feed it is too long - there is mention of "a model for text repunctuation and recapitalization", which I wonder if it could be used to break a very long text (eg a book) into pieces that can be digested by the tts engine (link: https://habr.com/ru/post/581960/) - as mentioned in another post, if you want a simple 'convert_this_text_

> what do I type in my shell to convert some_txt.txt to some_txt.wav Doesn't look like they have any command line tool included, but they have a simple Python example in the README. I used that, added some argparse around it and build a Nix package out of it. In case you are running Nix with flakes enabled, you can just type: nix run github:grumbel/silero-test -- -t "Hello World" --speaker en_0 -o /tmp/out.wav Source is pretty much "embarrassingly simple": https://github.com/Grumbel/silero-test/blob/master/silero-test It's currently hard codes the English language model, other models can be found at https://models.silero.ai/models/tts/ PS: This is probably reinventing the wheel, haven't looked around if there is anything ready to use already.