It is based on onnx, so can i use with transformers.js and the browser?
Show HN: Three new Kitten TTS models – smallest less than 25MB
151–160 of 201 posts
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#152It is based on onnx, so can i use with transformers.js and the browser?
Yes, someone already made a web demo for it: https://github.com/clowerweb/kitten-tts-web-demo (7 months ago). WebGPU support was marked experimental there, but transformer.js v4 (released last month) seems more stable now with some runtime/perf improvements: https://huggingface.co/blog/transformersjs-v4#performance--r...
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#153Whats the training data for this?
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#154Is this open-source or open-weights ML?
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#155Whats the training data for this?
Sounds like the voice actors from Critical Role but I just came off of watching 48 hours of Campaign 3 so I'm probably imagining things.
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#156I created a CLI wrapper for Kitten TTS: https://github.com/newptcai/purr BTW, it seems that kitten (the Python package) has the following chain of dependencies: kittentts → misaki[en] → spacy-curated-transformers So if you install it directly via uv, it will pull torch and NVIDIA CUDA packages (several GB), which are not needed to run kitten.
Thanks, your install script worked for me. In case it helps anyone else, the first time I tried to run purr I got "OSError: PortAudio library not found". Installing libportaudio (apt install libportaudio2) got it running.
Also did create a cli. I had to fork the project and removed one unused import which allowed me to remove a lot of unused ml libraries: https://github.com/Mic92/puss-say
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#157Earlier quoted context omitted.
Thanks, your install script worked for me. In case it helps anyone else, the first time I tried to run purr I got "OSError: PortAudio library not found". Installing libportaudio (apt install libportaudio2) got it running.
Also did create a cli. I had to fork the project and removed one unused import which allowed me to remove a lot of unused ml libraries: https://github.com/Mic92/puss-say
Unfortunately upstream never looks at any pull requests.
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#158Is this open-source or open-weights ML?
yes, indeed. we are working on adding mit licensed phonemizers too by this weekend, so you'll be able to use these models as you like :)
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#159Earlier quoted context omitted.
How is the Bruno voice for this one? there will also be another release in ~15-20 days where we have more professional voices. if you'd like to get early access and give feedback lmk, or dm me.
Hey Rohan, love to contribute feedback. Huge fan of Ava multilingual and hopefully there are many other others with similar taste, so my feedback might shape things towards a halfway decent direction at least for some. btw, use case is most often to listen to news/articles.
got it, this is very useful. thanks a lot.
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#160[dead]