Show HN: Three new Kitten TTS models – smallest less than 25MB • Hacker News Board

Re: Show HN: Three new Kitten TTS models – smallest less than 25MB

#11

Post by rohan_joshi » Thu, Mar 19, 2026, 4:51 PM UTC

Tacite wrote: post #4

Is it English only?

as of now its english only. the training for multilingual model is underway and should be out in April! what languages are you most interested in? Right now, we are providing deployments for custom languages + voices through support form on the github.

Re: Show HN: Three new Kitten TTS models – smallest less than 25MB

#12

Post by ks2048 » Thu, Mar 19, 2026, 4:52 PM UTC

There's a number of recent, good quality, small TTS models.

If the author doesn't describe some detail about the data, training, or a novel architecture, etc, I only assume they just took another one, do a little finetuning, and repackage as a new product.

Re: Show HN: Three new Kitten TTS models – smallest less than 25MB

#13

Post by okokwhatever » Thu, Mar 19, 2026, 4:54 PM UTC

ks2048 wrote: post #12

There's a number of recent, good quality, small TTS models. If the author doesn't describe some detail about the data, training, or a novel architecture, etc, I only assume they just took another one, do a little finetuning, and repackage as a new product.

[flagged]

Re: Show HN: Three new Kitten TTS models – smallest less than 25MB

#14

Post by rohan_joshi » Thu, Mar 19, 2026, 4:57 PM UTC

fwsgonzo wrote: post #10

How much work would it be to use the C++ ONNX run-time with this instead of Python? Is it a Claudeable amount of work? The iOS version is Swift-based.

shouldn't be hard. what backend/hardware are you interested in running this with? i'll add an example for using C++ onnx model. btw check out roadmap, our inference engine will be out 1-2 weeks and it is expected to be faster than onnx.

Re: Show HN: Three new Kitten TTS models – smallest less than 25MB

#15

Post by the_duke » Thu, Mar 19, 2026, 4:57 PM UTC

ks2048 wrote: post #12

There's a number of recent, good quality, small TTS models. If the author doesn't describe some detail about the data, training, or a novel architecture, etc, I only assume they just took another one, do a little finetuning, and repackage as a new product.

Any recommendations?

Re: Show HN: Three new Kitten TTS models – smallest less than 25MB

#16

Post by rohan_joshi » Thu, Mar 19, 2026, 5:00 PM UTC

kevin42 wrote: post #6

What 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.

Re: Show HN: Three new Kitten TTS models – smallest less than 25MB

#17

Post by rohan_joshi » Thu, Mar 19, 2026, 5:02 PM UTC

altruios wrote: post #5

One 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?

Re: Show HN: Three new Kitten TTS models – smallest less than 25MB

#18

Post by rohan_joshi » Thu, Mar 19, 2026, 5:20 PM UTC

ks2048 wrote: post #8

You should put examples comparing the 4 models you released - same text spoken by each.

great idea, let me add this. meanwhile, you can try the models on our huggingface spaces demo here: https://huggingface.co/spaces/KittenML/KittenTTS-Demo

Re: Show HN: Three new Kitten TTS models – smallest less than 25MB

#19

Post by wiradikusuma » Thu, Mar 19, 2026, 5:31 PM UTC

I'm thinking of giving "voice" to my virtual pets (think Pokemon but less than a dozen). The pets are made up animals but based on real animal, like Mouseier from Mouse (something like that). Is this possible?

Tldr: generate human-like voice based on animal sound. Anyway maybe it doesn't make sense.

Re: Show HN: Three new Kitten TTS models – smallest less than 25MB

#20

Post by magicalhippo » Thu, Mar 19, 2026, 5:31 PM UTC

A lot of good small TTS models in recent times. Most seem to struggle hard on prosody though.

Kokoro TTS for example has a very good Norwegian voice but the rhythm and emphasizing is often so out of whack the generated speech is almost incomprehensible.

Haven't had time to check this model out yet, how does it fare here? What's needed to improve the models in this area now that the voice part is more or less solved?