Kokoro gives pretty good voices and is quite light...making it useful despite its lack of voice cloning capability. However, I haven't figured out how to run it in the context of a tts server without homebrewing the server...which maybe is easy? IDK.
Kokoro WebGPU: Real-time text-to-speech 100% locally in the browser
21–30 of 56 posts
Re: Kokoro WebGPU: Real-time text-to-speech 100% locally in the browser
#22Fyi I tried this on my Galaxy S21 with both Brave and Chrome browsers and just got screeching noises in the audio
the mere idea of voice software's error mode being uncontrollable screeching is the most hilarious thing to me
Re: Kokoro WebGPU: Real-time text-to-speech 100% locally in the browser
#23Sounds horribly in chrome with an amd gpu, why is that?
Are you somehow implying that everyone in the AI arms race believes that only CUDA exists?! /s
But, in a more serious tone: the story that I hear about AMD GPUs is that they are, in fact, shittier because AMD themselves give fewer shits. GIGO
Re: Kokoro WebGPU: Real-time text-to-speech 100% locally in the browser
#24Kokoro gives pretty good voices and is quite light...making it useful despite its lack of voice cloning capability. However, I haven't figured out how to run it in the context of a tts server without homebrewing the server...which maybe is easy? IDK.
Re: Kokoro WebGPU: Real-time text-to-speech 100% locally in the browser
#25holy cow, how did they get the OpenAI voices like Alloy and Echo, generated in-browser and sounding 99% the same?
this is astounding
Re: Kokoro WebGPU: Real-time text-to-speech 100% locally in the browser
#26Brilliant job! Love how fast it is, I'm sure if the rapid pace of speech ML continues we'll have Speech to Speech models directly running in our browser!
It's already there, Hibiki by Kyutai.org was released yesterday with speech to speech, french to english on Iphone:
Re: Kokoro WebGPU: Real-time text-to-speech 100% locally in the browser
#27Re: Kokoro WebGPU: Real-time text-to-speech 100% locally in the browser
#28Brave browser and Samsung Galaxy S22 ultra - gives horrible screeching noises
Firefox on Samsung S21, worked fine albeit slow, around 20-25s for the demo text. Quality sounded good compared to a lot of other small TTS models I've tried.
Yeah this only worked with Firefox on my phone. All other browsers generated a screechy noise instead.
Re: Kokoro WebGPU: Real-time text-to-speech 100% locally in the browser
#29Generating audio takes a bit, but wow, 92MB model for really decent sounding speech. Is there a way to plug this thing into speech dispatcher on Linux and use for accessibility?
Re: Kokoro WebGPU: Real-time text-to-speech 100% locally in the browser
#30Amazing ! This is my first time witnessing a model of such prowess run in browser. Curious about quantization and webml