Kokoro TTS is the latest lightweight and high-performance text-to-speech (TTS) model for 2025. The generated audio is almost indistinguishable from that of a real person in terms of tone and intonation. You can give it a try at this link.
What’s even more impressive is that its model parameters are minimal, which means it can run smoothly on a regular CPU and GPU in a home computer. Moreover, it supports generating American English, British English, Spanish, French, Hindi, Italian, Japanese, Brazilian Portuguese, and Mandarin Chinese.
I’ve been using the AwesomeTTS plugin to generate audio in Anki with the free service, and I’ve always felt that the quality of the generated audio wasn’t up to par. So, I installed the Kokoro TTS model locally, and also made improvements to the AwesomeTTS, adding the ability to call the local Kokoro service.
First, you need to disable or remove the AwesomeTTS plugin from the Anki plugin page. Then, enter the plugin code 903988322 to install the AwesomeTTS-AI-Version (unofficial).
Now, in order to download KokoroTTS model, if you are a programmer and familiar with Docker, please refer to this tutorial. Otherwise, please see this tutorial.
Liên kết hỗ trợ
Reviews (12)
👍 2026-02-27
It’s running well on my mac. But I was wondering if there is a way that I could add audios with multiple voices. That would be even better
👍 2025-12-01
Didn’t work for me at all. I’ve tried both methods (GPU and CPU). The guide includes error prompt. And i have the same prompt. I’ve tried to restart pc, always made sure that the container was ranning. But it doesn’t work anyway. I hope the others will be lucky. At least try.
👍 2025-11-14
很棒的一个插件，不过现在还不能支持日语和中文这两个我平时最常遇到的两个语言，实在太可惜了吧哎
👍 2025-08-08
Works perfect on 25.07 newest version macos M1 without problems using docker
👍 2025-07-18
Maybe user error but I selected voice ef_dora and its like actually atrocious. reads every spanish word in English. Do I need to give it IPA? (sorry) This doesn’t sound bad at all though so Im confused what the issue is? https://fal.ai/models/fal-ai/kokoro/spanish/playground The DEBUG console does show this tho so yeah idk Searching for voice in path: /app/api/src/voices/v1_0 02:01:21 AM | DEBUG | Using single voice path: /app/api/src/voices/v1_0/ef_dora.pt 02:01:21 AM | DEBUG | Using vo
👍 2025-05-31
It works! This will really speed up my card creation process. Thank you!
👍 2025-04-20
This one worked realy well to me! just following the instructions in github and done! You saved me a lot!
👍 2025-02-23
Very well done! Simple to use and the tutorial was very easy to understand. Just one question about the language support. I read that Japanese and Chinese isn’t fully support yet. Will this be added at a later time? Thank you!
👍 2025-02-17
Exactly what i wanted. Unfortunately can’t figure out running with GPU for my mac
👍 2025-02-13
I have no idea how to use it, based on the description. What is Kokoro? I mean how to use it at my PC and not with a paid ai account in some service? o.O upd.: I’ve changed the feedback just now because of author’s update. But I actually don’t need this addon anymore since successfully generated sounds via official addon and google translate voice. It’s not bad at all. I hopy the addon will help to a lot of people anyway. Comment from author before post was edited I have updated a tutorial. You
👍 2025-02-13
Pretty cool
👍 2025-02-12
I haven’t tested this, but it is interesting idea. How to install kokori? Could you provide a full description of installation process or links? Comment from author I have updated a tutorial. You can take a look at it.
