Is there a paper describing the architecture of the model?
Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model
171–180 of 383 posts
Re: Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model
#172Earlier quoted context omitted.
There are still people who use machine wide python installs instead of environments? Python dependency hell was already bad years ago, but today it's completely impractical to do it this way. Even on raspberries.
Debian pretty much "solved" this by making pip refuse to install packages if you are not in an venv.
It needed distro buy in and implementation, but this is from the Python side: https://peps.python.org/pep-0668/
Re: Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model
#173Microsoft's and some of Google's TTS models make the simplest mistakes. For instance, they sometimes read "i.e." as "for example." This is a problem if you have low vision and use TTS for, say, proofreading your emails. Why does it happen? I'm genuinely curious.
Well, speech synthesizers are pretty much famous for speaking all sorts of things wrong. But what I find very concerning about LLM based TTS is that some of them cant really speak numbers greater then 100. They try, but fail a lot. At least tts-1-hd was pretty much doing this for almost every 3 or 4 digit number. Especially noticeable when it is supposed to read a year number.
Not entirely related but humans have the same problem.
For scriptwriting when doing voice overs we always explicitly write out everything. So instead of 1 000 000 we would write one million or a million. This is a trivial example but if the number was 1 548 736 you will almost never be able to just read that off. However one million, five hundred and forty eight thousand, seven hundred and thirty six can just be read without parsing.
Same with urls, W W W dot Google dot com.
Re: Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model
#174Earlier quoted context omitted.
There are still people who use machine wide python installs instead of environments? Python dependency hell was already bad years ago, but today it's completely impractical to do it this way. Even on raspberries.
Debian pretty much "solved" this by making pip refuse to install packages if you are not in an venv.
IIRC that's actually a change in upstream pip.
Re: Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model
#175Earlier quoted context omitted.
https://github.com/KittenML/KittenTTS/issues/17
> IANAL, but AFAICS this leaves 2 options, switching the license or removing that dependency. There is a third option: asking the project for an exception. Though that is unlikely to be granted¹ leaving you back with just the other two options. And of course a forth choice: just ignore the license. This is the option taken by companies like Onyx, whose products I might otherwise be interested in… ---- [1] Those of us…
> There is a third option: asking the project for an exception.
IIUC, the project isn't at the liberty to grant such an exception because it inherits its GPL license from espeak-ng.
Re: Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model
#176System Requirements Works literally everywhere Haha, on one of my machines my python version is too old, and the package/dependencies don't want to install. On another machie the python version is too new, and the package/dependencies don't want to install.
We are working to fix that. Thanks
Just point people to uv/uvx.
Re: Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model
#177Earlier quoted context omitted.
> IANAL, but AFAICS this leaves 2 options, switching the license or removing that dependency. There is a third option: asking the project for an exception. Though that is unlikely to be granted¹ leaving you back with just the other two options. And of course a forth choice: just ignore the license. This is the option taken by companies like Onyx, whose products I might otherwise be interested in… ---- [1] Those of us…
> There is a third option: asking the project for an exception. IIUC, the project isn't at the liberty to grant such an exception because it inherits its GPL license from espeak-ng.
Ah, yes, good catch, I didn't look deeper into the dependency tree at all. I'll update my footnote to include that as one of the reasons an exception may be impossible (or at least highly impractical).
Re: Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model
#178What I am still looking for is a way to clone voice locally. I have OK hardware. For example I can use Mistral Small 3.1 or what it is called locally. Premade voices can be interesting too, but I am looking for custom voice. Perhaps by providing audio and the corresponding transcript to the model, training it, and then give it a new text and let it speak that.
Re: Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model
#179Earlier quoted context omitted.
Have you considered offering a uvx command to run to get people going quickly?
Though I think you would still need to have the Python build dependencies installed for that to work.
If you restrict your dependencies to only those for which wheels are available, then uv should just be able to handle them for you.
Re: Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model
#180Earlier quoted context omitted.
Speech speed is always a tunable parameter and not something intrinsic to the model. The comparison to make is expressiveness and correct intonation for long sentences vs something like espeak. It actually sounds amazing for the size. The closest thing is probably KokoroTTS at 82M params and ~300MB.
I think he meant overacting typical for English dubs.
The voices sound artificial and a bit grating. The male voices especially are lacking, especially in depth: only the ultimate voice has any depth at all, while the others sound like teenagers who haven't finished puberty. None of the voices sound quite human, but they're all very annoying, and part of that is that they sound like they're acting.