{"slug": "kitten-tts", "name": "Kitten TTS", "category": "ai", "category_name": "AI tools and apps", "description": "", "recommenders": 5, "commenters": 12, "warners": 2, "score": 3.695, "rising": -1.64, "first": "2026-01-23", "latest": "2026-07-25", "why": "I'd also recommend checking out KittenTTS[2], I use it and it's great for the size/performance.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 5, "neutral": 3, "compare": 2, "warn": 2}, "spark": [0, 0, 2, 0, 2, 1, 0, 0, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I'd also recommend checking out KittenTTS[2], I use it and it's great for the size/performance.", "kind": "", "icon": true, "domain": null, "github_repo": "github.com/kittenml/kittentts", "official_url": "https://github.com/KittenML/KittenTTS", "pricing": "", "aliases": ["Kitten TTS", "KittenTTS"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 764485969, "item_id": 47780373, "url": "https://news.ycombinator.com/item?id=47780373", "by": "mowmiatlas", "date": "2026-04-15", "version": null, "stance": "recommend", "quote": "KittenTTS runs fine on the exact same hardware", "excerpt": "Extra context since the post got long. A few things that ate more time than I expected: Streaming was the worst one. Kokoro doesn't expose a streaming interface as far as I could find, you hand it a chunk of text, it gives you back the full audio for that chunk. For a reading app you can't wait for a whole paragraph before playback starts, so the whole streaming layer had to be built on top. I didn't want to process ", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: I built on-device TTS app because I run out of audiobooks on a flight"}, {"id": 759075137, "item_id": 47442196, "url": "https://news.ycombinator.com/item?id=47442196", "by": "kevin42", "date": "2026-03-19", "version": null, "stance": "recommend", "quote": "I'm impressed with the quality given the size.", "excerpt": "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", "context": "", "use_case": "text-to-speech", "switched_from": "", "story": "Show HN: Three new Kitten TTS models \u2013 smallest less than 25MB"}, {"id": 758475210, "item_id": 47404700, "url": "https://news.ycombinator.com/item?id=47404700", "by": "bachittle", "date": "2026-03-16", "version": null, "stance": "recommend", "quote": "Kitten TTS is good as a small model, better than Kokoro", "excerpt": "Coqui TTS is actually deprecated, the company shut down. I have a voice assistant that is using gpt-5.4 and opus 4.6 using the subsidized plans from Codex and Claude Code, and it uses STT and TTS from mlx-audio for those portions to be locally hosted: https://github.com/Blaizzy/mlx-audio Here are the following models I found work well: - Qwen ASR and TTS are really good. Qwen ASR is faster than OpenAI Whisper on Appl", "context": "", "use_case": "", "switched_from": "", "story": "My Journey to a reliable and enjoyable locally hosted voice assistant"}, {"id": 748953232, "item_id": 46809577, "url": "https://news.ycombinator.com/item?id=46809577", "by": "freakynit", "date": "2026-01-29", "version": null, "stance": "recommend", "quote": "A 25MB TTS model", "excerpt": "A 25MB TTS model: https://github.com/kittenml/kittentts", "context": "", "use_case": "local text-to-speech", "switched_from": "", "story": "Ask HN: What's the current best local/open speech-to-speech setup?"}, {"id": 747857152, "item_id": 46741072, "url": "https://news.ycombinator.com/item?id=46741072", "by": "soulofmischief", "date": "2026-01-23", "version": null, "stance": "recommend", "quote": "I'd also recommend checking out KittenTTS[2], I use it and it's great for the size/performance.", "excerpt": "I have a great local assistant that works end-to-end with voice. It's built on local, web-first technologies, it fits small LLMs in memory and manages inference and TTS/STT without stuttering. I've been shaping it up over a couple years and constantly switching out new models. If you want something simple that runs in browser, look at vosk-browser[0] and vits-web[1]. I'd also recommend checking out KittenTTS[2], I us", "context": "builds a local voice assistant", "use_case": "local text-to-speech", "switched_from": "", "story": "Ask HN: What's the current best local/open speech-to-speech setup?"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 759173696, "item_id": 47448356, "url": "https://news.ycombinator.com/item?id=47448356", "by": "dawdler-purge", "date": "2026-03-19", "version": null, "stance": "warn", "quote": "it will pull torch and NVIDIA CUDA packages (several GB), which are not needed to run kitten", "excerpt": "I 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 \u2192 misaki[en] \u2192 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.", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Three new Kitten TTS models \u2013 smallest less than 25MB"}, {"id": 759162112, "item_id": 47447632, "url": "https://news.ycombinator.com/item?id=47447632", "by": "deathanatos", "date": "2026-03-19", "version": null, "stance": "warn", "quote": "It also then crashes for me, with:", "excerpt": "It's mostly torch, I think. It pulls in NVIDIA libs (which \u2026 makes sense, I guess), and NVIDIA is just not at all judicious when it comes to disk space. I literally run out of disk trying to install this on Linux. On macOS, it's a markedly different experience: it's only ~700 MiB there; I'm assuming b/c no NVIDIA libs get pulled in, b/c why would they. For anyone who might want to play around with this: I can get dow", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Three new Kitten TTS models \u2013 smallest less than 25MB"}]}], "who": [{"by": "soulofmischief", "context": "builds a local voice assistant", "url": "https://news.ycombinator.com/item?id=46741072", "date": "2026-01-23"}], "tags": [], "use_cases": ["local text-to-speech", "text-to-speech", "text to speech"], "compared": [{"slug": "kokoro", "name": "Kokoro", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [{"id": 759083952, "item_id": 47442747, "url": "https://news.ycombinator.com/item?id=47442747", "by": "rohan_joshi", "date": "2026-03-19", "version": null, "stance": "neutral", "quote": "you can try the models on our huggingface spaces demo", "excerpt": "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", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Three new Kitten TTS models \u2013 smallest less than 25MB"}], "threads": [{"url": "https://news.ycombinator.com/item?id=47441546", "title": "Show HN: Three new Kitten TTS models \u2013 smallest less than 25MB", "mentions": 7}, {"url": "https://news.ycombinator.com/item?id=46731068", "title": "Ask HN: What's the current best local/open speech-to-speech setup?", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=49051323", "title": "Inflect-v2: 3.9M and 9.3M parameter open-weight TTS models", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47780234", "title": "Show HN: I built on-device TTS app because I run out of audiobooks on a flight", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47398534", "title": "My Journey to a reliable and enjoyable locally hosted voice assistant", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {"recommend": 2, "compare": 1}, "2026-02": {}, "2026-03": {"recommend": 2, "warn": 2, "neutral": 3}, "2026-04": {"recommend": 1}, "2026-05": {}, "2026-06": {}, "2026-07": {"compare": 1}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "versions": [], "version_unnamed": 0, "family_ref": null, "runs_on": null, "lines": [], "quotes": [{"id": 784821185, "item_id": 49051324, "url": "https://news.ycombinator.com/item?id=49051324", "by": "Nymbo", "date": "2026-07-25", "version": null, "stance": "compare", "quote": "competitive with much larger lightweight TTS systems, including KittenTTS, Piper, and Supertonic-3", "excerpt": "Introducing Inflect-v2, two exceptionally small, open-weight English TTS models at just 3.9M and 9.3M parameters. Both generate speech multiple times faster than real-time on CPU. Despite their size, Inflect-v2 delivers quality that is competitive with much larger lightweight TTS systems, including KittenTTS, Piper, and Supertonic-3. CPU, CUDA, PyTorch, and ONNX are supported. Apache 2.0. See it for yourselves: https", "context": "", "use_case": "", "switched_from": "", "story": "Inflect-v2: 3.9M and 9.3M parameter open-weight TTS models"}, {"id": 764485969, "item_id": 47780373, "url": "https://news.ycombinator.com/item?id=47780373", "by": "mowmiatlas", "date": "2026-04-15", "version": null, "stance": "recommend", "quote": "KittenTTS runs fine on the exact same hardware", "excerpt": "Extra context since the post got long. A few things that ate more time than I expected: Streaming was the worst one. Kokoro doesn't expose a streaming interface as far as I could find, you hand it a chunk of text, it gives you back the full audio for that chunk. For a reading app you can't wait for a whole paragraph before playback starts, so the whole streaming layer had to be built on top. I didn't want to process ", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: I built on-device TTS app because I run out of audiobooks on a flight"}, {"id": 759869392, "item_id": 47491837, "url": "https://news.ycombinator.com/item?id=47491837", "by": "ilnmtlbnm", "date": "2026-03-23", "version": null, "stance": "neutral", "quote": "Added kitten (nano only, for now, will move on to mini)", "excerpt": "I've been playing with running small models in browser tabs for some time, and finally decided to open some of it. Added kitten (nano only, for now, will move on to mini) to my \"web tts thing\": https://github.com/idle-intelligence/tts-web demo: https://idle-intelligence.github.io/tts-web/web/", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Three new Kitten TTS models \u2013 smallest less than 25MB"}, {"id": 759299761, "item_id": 47456235, "url": "https://news.ycombinator.com/item?id=47456235", "by": "ilyaizen", "date": "2026-03-20", "version": null, "stance": "neutral", "quote": "featuring Kitten TTS and other engines", "excerpt": "You might also like CopySpeak, a lightweight tool I've recently built for quick AI text-to-speech using the clipboard, featuring Kitten TTS and other engines. https://github.com/ilyaizen/CopySpeak", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Three new Kitten TTS models \u2013 smallest less than 25MB"}, {"id": 759214864, "item_id": 47450929, "url": "https://news.ycombinator.com/item?id=47450929", "by": "aratahikaru5", "date": "2026-03-19", "version": null, "stance": "neutral", "quote": "Yes, someone already made a web demo for it", "excerpt": "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--runtime-improvements", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Three new Kitten TTS models \u2013 smallest less than 25MB"}, {"id": 759173696, "item_id": 47448356, "url": "https://news.ycombinator.com/item?id=47448356", "by": "dawdler-purge", "date": "2026-03-19", "version": null, "stance": "warn", "quote": "it will pull torch and NVIDIA CUDA packages (several GB), which are not needed to run kitten", "excerpt": "I 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 \u2192 misaki[en] \u2192 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.", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Three new Kitten TTS models \u2013 smallest less than 25MB"}, {"id": 759162112, "item_id": 47447632, "url": "https://news.ycombinator.com/item?id=47447632", "by": "deathanatos", "date": "2026-03-19", "version": null, "stance": "warn", "quote": "It also then crashes for me, with:", "excerpt": "It's mostly torch, I think. It pulls in NVIDIA libs (which \u2026 makes sense, I guess), and NVIDIA is just not at all judicious when it comes to disk space. I literally run out of disk trying to install this on Linux. On macOS, it's a markedly different experience: it's only ~700 MiB there; I'm assuming b/c no NVIDIA libs get pulled in, b/c why would they. For anyone who might want to play around with this: I can get dow", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: Three new Kitten TTS models \u2013 smallest less than 25MB"}, {"id": 759075137, "item_id": 47442196, "url": "https://news.ycombinator.com/item?id=47442196", "by": "kevin42", "date": "2026-03-19", "version": null, "stance": "recommend", "quote": "I'm impressed with the quality given the size.", "excerpt": "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", "context": "", "use_case": "text-to-speech", "switched_from": "", "story": "Show HN: Three new Kitten TTS models \u2013 smallest less than 25MB"}, {"id": 758475210, "item_id": 47404700, "url": "https://news.ycombinator.com/item?id=47404700", "by": "bachittle", "date": "2026-03-16", "version": null, "stance": "recommend", "quote": "Kitten TTS is good as a small model, better than Kokoro", "excerpt": "Coqui TTS is actually deprecated, the company shut down. I have a voice assistant that is using gpt-5.4 and opus 4.6 using the subsidized plans from Codex and Claude Code, and it uses STT and TTS from mlx-audio for those portions to be locally hosted: https://github.com/Blaizzy/mlx-audio Here are the following models I found work well: - Qwen ASR and TTS are really good. Qwen ASR is faster than OpenAI Whisper on Appl", "context": "", "use_case": "", "switched_from": "", "story": "My Journey to a reliable and enjoyable locally hosted voice assistant"}, {"id": 749279296, "item_id": 46829956, "url": "https://news.ycombinator.com/item?id=46829956", "by": "d4rkp4ttern", "date": "2026-01-30", "version": null, "stance": "compare", "quote": "there\u2019s really no advantage over pocket TTS. There are some tradeoffs like Kitten doesn\u2019t have streaming audio.", "excerpt": "So I benchmarked it and there\u2019s really no advantage over pocket TTS. There are some tradeoffs like Kitten doesn\u2019t have streaming audio.", "context": "benchmarked it", "use_case": "text to speech", "switched_from": "", "story": "Ask HN: What's the current best local/open speech-to-speech setup?"}, {"id": 748953232, "item_id": 46809577, "url": "https://news.ycombinator.com/item?id=46809577", "by": "freakynit", "date": "2026-01-29", "version": null, "stance": "recommend", "quote": "A 25MB TTS model", "excerpt": "A 25MB TTS model: https://github.com/kittenml/kittentts", "context": "", "use_case": "local text-to-speech", "switched_from": "", "story": "Ask HN: What's the current best local/open speech-to-speech setup?"}, {"id": 747857152, "item_id": 46741072, "url": "https://news.ycombinator.com/item?id=46741072", "by": "soulofmischief", "date": "2026-01-23", "version": null, "stance": "recommend", "quote": "I'd also recommend checking out KittenTTS[2], I use it and it's great for the size/performance.", "excerpt": "I have a great local assistant that works end-to-end with voice. It's built on local, web-first technologies, it fits small LLMs in memory and manages inference and TTS/STT without stuttering. I've been shaping it up over a couple years and constantly switching out new models. If you want something simple that runs in browser, look at vosk-browser[0] and vits-web[1]. I'd also recommend checking out KittenTTS[2], I us", "context": "builds a local voice assistant", "use_case": "local text-to-speech", "switched_from": "", "story": "Ask HN: What's the current best local/open speech-to-speech setup?"}]}