I thought they were going to make kitten sounds instead of speech
I guess they are Discord kittens?
Show HN: Three new Kitten TTS models – smallest less than 25MB
131–140 of 201 posts
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#132One of the core features I look for is expressive control. Either in the form of the api via pitch/speed/volume controls, for more deterministic controls. Or in expressive tags such as [coughs], [urgently], or [laughs in melodic ascending and descending arpeggiated gibberish babbles]. the 25MB model is amazingly good for being 25MB. How does it handle expressive tags?
thank you so much. Right now, it cannot handle expressive tags. what kind of tags would be most helpful according to you?
not OP but something like [] where intention might be something like anger, curiousness, etc. [long pause], [gasp], [laughter] stuff like that.
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#133What I love about OpenClaw is that I was able to send it a message on Discord with just this github URL and it started sending me voice messages using it within a few minutes. It also gave me a bunch of different benchmarks and sample audio. I'm impressed with the quality given the size. I don't love the voices, but it's not bad. Running on an intel 9700 CPU, it's about 1.5x realtime using the 80M model. It wasn't an…
yeah we'll add some more professional-sounding voices and also support for diy custom voices. we tried to add more anime/cartoon-ish voices to showcase the expressivity. Regarding running on the 3080 gpu, can you share more details on github issues, discord or email? it should be blazing fast on that. i'll add an example to run the model on gpu too.
I wonder if it's possible to guide the intonation in any way.
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#134Earlier quoted context omitted.
Yes, we've started working on it and will have a range of stt models v soon. lmk if you have a prod use-case in mind?
Many of my use cases are similar to those of: Robert J. P. Oberg - (GitHub) ognistik Perhaps his YouTube channel is worth a watch. This video from four months ago compares various STT tools: https://youtu.be/pKU9CABtnOw Speaking of apps that would, if I had to guess, love to integrate you: FluidVoice is incredible and developing quickly. Handy is really hot right now. Also have VoiceInk out there, solid iOS option. […
Thank you for this link.
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#135What I love about OpenClaw is that I was able to send it a message on Discord with just this github URL and it started sending me voice messages using it within a few minutes. It also gave me a bunch of different benchmarks and sample audio. I'm impressed with the quality given the size. I don't love the voices, but it's not bad. Running on an intel 9700 CPU, it's about 1.5x realtime using the 80M model. It wasn't an…
I'm jealous. It took me far longer and much more frustration to get it to run. Had to get the right Python version and make sure it didn't break anything with the previous Python version. A friend suggested using Docker, so I started down that path until I realized I'd probably have to set the whole thing up there myself. Eventually got it to run and I think I didn't break anything else. I hate Python so much.
Two words; Nix Flakes
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#136Earlier quoted context omitted.
Thank you so much, that fixes an enormous pain point I was hitting. It's not just the size, that dependency chain was actually breaking on my machine and failing to install. Are we losing something by dropping the extra dependencies?
I don't think so. It is perhaps a bug to have this unnecessary dependency. I expect the author of kitten to fix this soon.
thanks a lot for helping w this. yes i'll fix this asap.
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#137I'd love to see a monolingual Japanese model sometime in the future. Qwen3-tts works for Japanese in general, but from time to time it will mix with some Mandarin in between, making it unusable.
our next model(eta 3ish weeks) will support Japanese. would love to get your feedback then on how the quality is. can you share what usecase you want? would love to support it.
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#138What I love about OpenClaw is that I was able to send it a message on Discord with just this github URL and it started sending me voice messages using it within a few minutes. It also gave me a bunch of different benchmarks and sample audio. I'm impressed with the quality given the size. I don't love the voices, but it's not bad. Running on an intel 9700 CPU, it's about 1.5x realtime using the 80M model. It wasn't an…
I'm jealous. It took me far longer and much more frustration to get it to run. Had to get the right Python version and make sure it didn't break anything with the previous Python version. A friend suggested using Docker, so I started down that path until I realized I'd probably have to set the whole thing up there myself. Eventually got it to run and I think I didn't break anything else. I hate Python so much.
damnn, really sorry for the inconv, looks like some folks are having bad env issues. we're working on fixing this.
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#139Earlier quoted context omitted.
I'm jealous. It took me far longer and much more frustration to get it to run. Had to get the right Python version and make sure it didn't break anything with the previous Python version. A friend suggested using Docker, so I started down that path until I realized I'd probably have to set the whole thing up there myself. Eventually got it to run and I think I didn't break anything else. I hate Python so much.
Nowadays these frustrations shouldn't be a thing any more. If the author used uv, the script would be able to install its own dependencies and just work.
yeah let me add uv and conda support to make it easier.
Re: Show HN: Three new Kitten TTS models – smallest less than 25MB
#140Earlier quoted context omitted.
why you don't use some kind of environment, Conda or something like that?
I used uv, which should have generated a stable environment. No dice. There's a bug in spacey. I suspect success is highly variable on macOS vs. Linux; the spacey bug is only in newer (3.14 only or later) Pythons, which Linux will have.
thanks for pointing these errors out. we're looking into this and will help fix this.