[dead]
Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro
91–100 of 107 posts
Re: Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro
#92I don't want to mess with port numbers and gpu cards; I just want an upgrade from the age-old:
apt install festival
Re: Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro
#93This is awesome.
People are already talking about use of local models for heavy tasks like llm inference. TTS is very much possible on device without any high end gpu.
That's why Ive been working integrating it into a free reader web app with some features more than just getting audio from a text.
Re: Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro
#94I just hooked it up to my personal AI Japanese Teacher app, pretty good quality / natural sounding speech in mixed English / Japanese while running fast on CPU so I don't waste VRAM.
For Japanese TTS, AivisSpeech-Engine[1] works really well with mixed Japanese/English text in my experience. They also provide container images on ghcr.io for both CPU and GPU inference.
Re: Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro
#95I was kind of waiting for Apple to ship something like this and using speechify in the meantime, so I was pleasantly surprised to stumble across Kokoro in a thread on HN a few days ago. The voices are better than the cloud provider IMO.
I'm using it in an open source tool I built for listening to coding agents instead of watching them work, and it's been great. Local, private, free to run, and enough voices that I can actually use a different one for each agent.
Wrote a bit more about the project here: https://jonmagic.com/posts/i-stopped-watching-my-agents-work...
Re: Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro
#96I was kind of waiting for Apple to ship something like this and using speechify in the meantime, so I was pleasantly surprised to stumble across Kokoro in a thread on HN a few days ago. The voices are better than the cloud provider IMO. I'm using it in an open source tool I built for listening to coding agents instead of watching them work, and it's been great. Local, private, free to run, and enough voices that I ca…
You mean it's better than the speechify cloud provided voices?
Re: Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro
#97[flagged]
Re: Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro
#98I was kind of waiting for Apple to ship something like this and using speechify in the meantime, so I was pleasantly surprised to stumble across Kokoro in a thread on HN a few days ago. The voices are better than the cloud provider IMO. I'm using it in an open source tool I built for listening to coding agents instead of watching them work, and it's been great. Local, private, free to run, and enough voices that I ca…
You mean it's better than the speechify cloud provided voices?
Correct. In my experience so far (2 days of usage across a couple dozen voices on speechify and then Kokoro) I've preferred the ones from Kokoro.
Re: Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro
#99Off-topic, re: “kokoro” Article refers to: https://huggingface.co/hexgrad/Kokoro-82M Caught my eye for the related name to my book of Kakuro puzzles for sale at https://www.kakurokokoro.com Kokoro comes from the Japanese word meaning something like heart or spirit, and not the literal ones.
Also from this: https://terminator.fandom.com/wiki/Kokoro
It seems all three are equally obscure. Mine at least is a heart shape :)
Re: Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro
#100I have used Kokoro fairly extensively for an accessibility product. I have loved working with it (especially because I don't have an NVidia GPU like many TTS of similar quality require). I particularly appreciate the fact that it lets you manually add IPA pronunciation guides. There have been some cases where an important word is a homograph and Kokoro assumed the wrong pronunciation. The place where it falls a littl…
Same trick with many others. I say "Knight" to Wispr or Google and see "night". I say "Knight to f3", and just backspace out "to f3".
Of course, over time, I use custom entries.
My snippet expansion entry in Wispr is "Chess Knight" = "Knight" ("Knight to f3" without customization was more reliable than "Chess Knight")
I also use "dot bullet" = "•", as I like to separate thoughts with • more than ;