@Nymbo on Hugging Face: "Introducing Inflect-v2, two exceptionally small, open-weight English TTS…"

Log In<br>Sign Up

Me:\n\nDoesn't believe the post\nClicks into the Hugging Face model\nListens to the audio sample\nHoly crap no way this is real\nDownloads it and realizes it is real.\n\n","updatedAt":"2026-07-25T19:32:54.985Z","author":{"_id":"69d98a53d35e3010a3cfb1da","avatarUrl":"/avatars/214c539fd611e3418031d75c84dd5637.svg","fullname":"Leo Lennox","name":"leo-lennox","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8760797381401062},"editors":["leo-lennox"],"editorAvatarUrls":["/avatars/214c539fd611e3418031d75c84dd5637.svg"],"reactions":[{"reaction":"🤯","users":["owensong","Nymbo","X-xxx-X","elizabethgong"],"count":4},{"reaction":"😎","users":["Nymbo"],"count":1}],"isReport":false}},{"id":"6a65109aecc88b3bca666d93","author":{"_id":"642374c46e61cda1b3a1c735","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/VUcBJ7SAwpo9FL-P3yDD8.png","fullname":"Owen Song","name":"X-xxx-X","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false},"createdAt":"2026-07-25T19:38:02.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"Crazy work bro, this is genuinely so impressive for the model size. This might be THE text-to-speech model of the year. ","html":"Crazy work bro, this is genuinely so impressive for the model size. This might be THE text-to-speech model of the year. \n","updatedAt":"2026-07-25T19:38:02.444Z","author":{"_id":"642374c46e61cda1b3a1c735","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/VUcBJ7SAwpo9FL-P3yDD8.png","fullname":"Owen Song","name":"X-xxx-X","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9167097806930542},"editors":["X-xxx-X"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/VUcBJ7SAwpo9FL-P3yDD8.png"],"reactions":[{"reaction":"❤️","users":["owensong","Nymbo"],"count":2}],"isReport":false}}],"numComments":2},"theme":"light","acceptLanguages":["*"],"primaryEmailConfirmed":false,"canCreateKernels":false}">Join the conversation<br>Join the community of Machine Learners and AI enthusiasts.<br>Sign Up

Back to feed

Nymbo  posted an update about 1 hour ago

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:<br>owensong/Inflect-Micro-v2<br>owensong/Inflect-Nano-v2

Try the Demos:<br>Nymbo/Inflect-TTS (unlimited CPU usage)<br>owensong/Inflect-v2 (ultra-fast ZeroGPU usage) See translation

🔥

🚀

leo-lennox<br>about 1 hour ago

Me:

Doesn't believe the post

Clicks into the Hugging Face model

Listens to the audio sample

Holy crap no way this is real

Downloads it and realizes it is real.

See translation<br>🤯

😎

Reply

X-xxx-X<br>about 1 hour ago

Crazy work bro, this is genuinely so impressive for the model size. This might be THE text-to-speech model of the year.

See translation<br>❤️

Reply

In this post

Nymbo Nymbo Follow

leo-lennox Leo Lennox Follow

X-xxx-X Owen Song Follow