Web version: https://clowerweb.github.io/kitten-tts-web-demo/ It sounds ok, but impressive for the size.
This doesn’t seem to work on Safari. Works great on Chrome, though
Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model
101–110 of 383 posts
Re: Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model
#102The headline feature isn’t the 25 MB footprint alone. It’s that KittenTTS is Apache-2.0. That combo means you can embed a fully offline voice in Pi Zero-class hardware or even battery-powered toys without worrying about GPUs, cloud calls, or restrictive licenses. In one stroke it turns voice everywhere from a hardware/licensing problem into a packaging problem. Quality tweaks can come later; unlocking that deployment…
yeah, we are super excited to build tiny ai models that are super high quality. local voice interfaces are inevitable and we want to power those in the future. btw, this model is just a preview, and the full release next week will be of much higher quality, along w another ~80M model ;)
Re: Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model
#103 System Requirements
Works literally everywhere
On another machie the python version is too new, and the package/dependencies don't want to install.
Re: Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model
#104Kudos guys!
Thanks
Re: Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model
#105Can you run it in reverse for speech recognition?
We will release an STT model as well.
Re: Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model
#106it would be great if there is typescript support in the future
Yup it runs on the web browser. https://clowerweb.github.io/kitten-tts-web-demo/
Re: Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model
#107Cool. While I think this is indeed impressive and has a specific use case (e.g. in the embedded sector), I'm not totally convinced that the quality is good enough to replace bigger models. With fish-speech[1] and f5-tts[2] there are at least 2 open source models pushing the quality limits of offline text-to-speech. I tested F5-TTS with an old NVidia 1660 (6GB VRAM) and it worked ok-ish, so running it on a little more…
We have released just a preview of the model. We hope to get the model much better in the future releases.
Re: Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model
#108I don't mind so much the size in MB, the fact that it's pure CPU and the quality, what I do mind however is the latency. I hope it's fast. Aside: Are there any models for understanding voice to text, fully offline, without training? I will be very impressed when we will be able to have a conversation with an AI at a natural rate and not "probe, space, response"
Any idea what factors play into latency in TTS models?
Mostly model size, and input size. Some models which use attention are O(N^2)
Re: Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model
#109Re: Show HN: Kitten TTS – 25MB CPU-Only, Open-Source TTS Model
#110Earlier quoted context omitted.
A robotic, explicitly non-natural voice would be perfectly acceptable, and even desirable, in many situations[...]it'd be enough is the speech if easy to recognize. We've had formant synths for several decades, and they're perfectly understandable and require a tiny amount of computing power, but people tend not to want to listen to them: https://en.wikipedia.org/wiki/Software_Automatic_Mouth https://simulationcorner…
Well, this one is a bit too jarring to the ears.
I think it's charming