Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro

Join the discussion

• Hacker News
• Yeah, we need to keep up with how quickly AI types back to us, typing on the keyboards is no longer quick enough, gotta dictate everything now.
  by othmanosx
• Great way to enter your passwords
  by croes
• This is the opposite way
  by victorbjorklund
• It crashes as soon as you put a little paragraph of text on Apple M2 Pro.

  Hard pass.

  Why do these half baked projects get all the attention and thousands of clicks when it just takes a simple thing to bring the whole castle down?

  by keyle
• curious to know if it comes with audio tags?
  by thenextan
• > Apple M2 Pro: 4.5 seconds

  > AMD Ryzen 7 8745HS: 1.5 seconds

  These two can probably do it much faster on their iGPUs.

  by lostmsu
• Yep, and Kokoro-FastAPI (which he already uses) makes it super easy with start-gpu_mac.sh
  by dygd
• On macOS I've been using piper (https://github.com/OHF-Voice/piper1-gpl) to announce claude code notifications and it works perfectly!
  by behnamoh
• I agree that Kokoro is a good TTS model.

  If you're interested in an ONNX version and a permissively licensed TTS Tokenizer, I built a pipeline for that a while back: https://huggingface.co/NeuML/kokoro-base-onnx

  by dmezzetti
• Has anyone tested/ported Kokoro To mobile?
  by stogot
• I don't want to just spew AI-hate, but is an LLM actually necessary for this? I haven't worked with, but came across loads of non-AI TTS tools. Are these now exceptionally better to justify the overhead? Genuinely asking.
  by thegarliccheese
• kokoro is very nice, but I am disappointed that this wasn't an announcement of a new kokoro version.
  by SubiculumCode
• I 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.
  by cat_plus_plus
• Was just thinking of making exactly that. I have made Kokoro the voice of my local LLM (qwen 3.6). What do you use for a Japanese tutor app?
  by JoeDaDude
• 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.

  [1]: https://github.com/aivis-project/AivisSpeech-Engine

  by usagisushi
• Another endorsement - I used Kokoro pretty extensively with an app I was developing over the last year and it's been excellent, both on- and off- GPU. Even with Elevenlabs (long time subscriber) the comparative quality of Kokoro keeps up really well until you get to their larger models with their professional voices.

  I do wish there were better support for SSML, as well as deeper documentation of how to influence inflection in-line, but the default does well with standard emphasis (e.g. putting asterisks around text elements). Both asks are getting outside the zone of reasonable asks for this sort of distribution, though, and I remain incredibly grateful for the quality of what hexgrad and nazdridoy have put out in the world.

  by rnxrx
• I've used Piper for local TTS before, and Kokoro looks like an interesting
  by icevl
• Anyone know which local TTS is best, close to Eleven Labs quality?
  by fady0
• F5-TTS
  by echelon
• https://github.com/rhulha/StreamingKokoroJS all in browser, 100% private, nothing tracked
  by raymond_goo
• I tried it but it did not function.
  by djmips
• When I hear the male voice I think: "Ok, it's the Youtube guy".
  by TurdF3rguson
• kokoro is surprisingly great at nuance but it's tough to improve that last ~2% or so. kokoro + rvc is really great too; i use that for ELEMENT47, the LLM-centric comedy podcast i do that i wish more people would listen to. (e47.net , feel free to subscribe!)
  by 0gs
• this is very cool! i also made a kokoro based tts tool which runs on a jetson orin kit. it serves tts generations over durable streams, try it out here: https://streamtts.dev/ , i also wrote about it: https://s2.dev/blog/local-ai
  by infiniteregrets
• Who is going to hack together a mac widget that allows us to select text anywhere, press a shortcut key and finally get a non robotic voice outputted in a reasonable amount of time?

  I am aware of the Option + Esc shortcut on osx for the onboard TTS but wow is it hard to listen to in 2026.

  by hdz
• In System Settings, if you go to Accessibility and click "Read & Speak" in the "Vision" section, you can select a different voice using the "System voice" section. Click the "(i)" to preview your various options and even download more. Some, like "Allison (Enhanced)," sound leagues better than the default voice.
  by Cyberdog
• Have you tried /usr/bin/say ? Might already have something sufficient for you - there’s quite a few voices there.
  by asteroidburger
• This is Amazing and a game changer. Millions were spent during NLP era to achieve even <50% what this model offers.

  Now this on a CPU is next level. When algorithms perform well on commodity hardware, the scale tips.

  This gives hope that CPULLM's are not far off that'll be just fine for majority of use cases.

  by namegulf
• Just ran on Podman on a older hardware with intel CPU processor and ubuntu linux.

  When given a large text, it nicely chunked them up (debug statements showed), generated the audio and played back nicely.

  Well done!

  by namegulf
• https://wlejon.github.io/kokoro-lab-web/

  You can tweak the pitch as well.

  by est