Kitten TTS
Hacker ApprovedRanked 5 of 18 text-to-speech models by recommenders
Open-source text-to-speech models under 25MB that people find impressively good for their size. Common caveats: cartoonish voices and trouble with numbers and domain-specific words.
Open-source text-to-speech models under 25MB that people find impressively good for their size. Common caveats: cartoonish voices and trouble with numbers and domain-specific words.
40 people gave an opinion
- recommend it
- 33
- criticize it
- 7
- approval share
- 83%
Recommended in 4 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: not recommended
- August 2026: not recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 33 people recommend itNeeds 10 or more, met.
- 4.7 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 4 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Beats earlier and other small models
“this version does much better than the precious one and is the best among other <25MB models”
Comment from 19 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB” “A very clear improvement from the first set of models you released some time ago.”
Comment from 19 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB” “This 15M is way better than the 80M model from our previous launch”
Comment from 19 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB” - Comment from 19 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB”
- Comment from 16 Mar 2026 in “My Journey to a reliable and enjoyable locally hosted voice assistant”
- Comment from 19 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB”
Impressive quality for its size
“I'm impressed with the quality given the size. I don't love the voices, but it's not bad.”
Comment from 19 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB” “for its size it's very impressive. Just has issues pronounciating numbers”
Comment from 19 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB” “25MB for a TTS model that's usable is a real achievement”
Comment from 20 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB” - Comment from 19 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB”
- Comment from 22 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB”
Tiny footprint under 25MB
“25mb is small enough that I think it'd be worth it”
Comment from 19 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB” “25MB is genuinely exciting for that use case.”
Comment from 20 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB” “The <25MB figure is what stands out.”
Comment from 20 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB” Expressive, high-quality output
“The 14M variant reaches new SOTA in expressivity among similar sized models”
Comment from 20 Feb 2026 in “Show HN: Three new models by KittenML. <25 MB Open-source TTS. Highly Expressive” “Really cool to see innovation in terms of quality of tiny models.”
Comment from 19 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB”
What people warn about
Each mark is one comment
Voices sound cartoonish or unserious
“I'm impressed with the quality given the size. I don't love the voices, but it's not bad.”
Comment from 19 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB” “The cute Kitten voices are nice, but I want something I can take seriously”
Comment from 19 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB” “All but one of the voices are unusable in a business context.”
Comment from 19 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB” - Comment from 19 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB”
Mispronounces numbers and domain words
“It sounded quite good indeed for the normal English stuff, but I guess predictably was quite bad at the domain-specific words.”
Comment from 19 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB” “for its size it's very impressive. Just has issues pronounciating numbers”
Comment from 19 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB” “Found they struggle with numbers.”
Comment from 20 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB” Heavy install dependencies like torch
“it will pull torch and NVIDIA CUDA packages (several GB), which are not needed to run kitten.”
Comment from 20 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB” “that dependency chain was actually breaking on my machine and failing to install”
Comment from 20 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB” “I literally run out of disk trying to install this on Linux.”
Comment from 19 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB” Missing docs and streaming audio
“it's weird that no "language" or "English" is mentioned on the github page”
Comment from 20 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB” “there’s really no advantage over pocket TTS. There are some tradeoffs like Kitten doesn’t have streaming audio.”
Comment from 30 Jan 2026 in “Ask HN: What's the current best local/open speech-to-speech setup?” “I couldn't locate how to run it on a GPU anywhere in the repo.”
Comment from 19 Mar 2026 in “Show HN: Three new Kitten TTS models – smallest less than 25MB”
Other text-to-speech models people recommend
The four most recommended other text-to-speech models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| ElevenLabs | 59 | 20 | 75% | 13 | — | Approved |
| Kokoro TTS | 59 | 9 | 87% | 11 | 1 mo3 owners | Approved |
| Pocket TTS | 41 | 16 | 72% | 8 | — | Approved |
| Qwen3-TTS | 41 | 13 | 76% | 7 | — | Approved |
| Kitten TTSThis page | 33 | 7 | 83% | 4 | — | Approved |
What people said
40 of the 49 comments that mention it, newest first. Each links to the original comment.
“KittenTTS runs fine on the exact same hardware AND the XCode simulator.”
“Bruno was the best of all the voices imo.”
“These sizes are incredibly impressive.”
“the resulting script was ~20 lines, very nice!”
“it's weird that no "language" or "English" is mentioned on the github page”
“25MB is genuinely exciting for that use case.”
“25MB for a TTS model that's usable is a real achievement”
“Found they struggle with numbers.”
“The <25MB figure is what stands out.”
“Good on device TTS is an amazing accessibility tool.”
“Not too bad, actually! Looking forward to hearing some more voices.”
“that dependency chain was actually breaking on my machine and failing to install”
“it will pull torch and NVIDIA CUDA packages (several GB), which are not needed to run kitten.”
“Huge fan of Ava multilingual”
“This is something I've been looking for”
“It sounded quite good indeed for the normal English stuff, but I guess predictably was quite bad at the domain-specific words.”
“The cute Kitten voices are nice, but I want something I can take seriously”
“I literally run out of disk trying to install this on Linux.”
“for its size it's very impressive. Just has issues pronounciating numbers”
“sounded very good though wasn't terribly challenging text”
“They sound like cartoon voices... but I really like them I could listen to a book with those.”
“our 15M model now is better than our previous 80M model”
“A very clear improvement from the first set of models you released some time ago.”
“This 15M is way better than the 80M model from our previous launch”
“I couldn't locate how to run it on a GPU anywhere in the repo.”
“Really cool to see innovation in terms of quality of tiny models.”
“it is superior in terms of pronunciation accuracy for less common words”
“The new 15M is way better than the previous 80M model(v0.1)”
“i think the 40M is quite similar to 80M for most usecases”
“this version does much better than the precious one and is the best among other <25MB models”
“25mb is small enough that I think it'd be worth it”
“I'm impressed with the quality given the size. I don't love the voices, but it's not bad.”
“the 25MB model is amazingly good for being 25MB”
“All but one of the voices are unusable in a business context.”
“Kitten TTS is good as a small model, better than Kokoro”
“this is what I'm excited about”
“The 14M variant reaches new SOTA in expressivity among similar sized models”
“there’s really no advantage over pocket TTS. There are some tradeoffs like Kitten doesn’t have streaming audio.”
“They should really make a uv-installable CLI tool like pocket-TTS did.”
“I use it and it's great for the size/performance.”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.