AnkiWeb addon 733203228
Enables text-to-speech playback of locally generated Kokoro audio via a configured Kokoro-FastAPI service URL and per-language voices, avoiding cloud latency and network or profile-switch failures on Linux.
Open on AnkiWeb GitHub Find alternatives
stale
| Min Anki | Max Anki | Updated |
|---|---|---|
| 2.1.1 | 25.02.7+ | 2025-07-28 |
Loading…
Generates high-quality Anki audio via a locally hosted Kokoro text-to-speech model or other OpenAI-compatible TTS services, supporting nine languages.
Synthesizes Japanese speech at review time via a local VOICEVOX server, with centrally routed voice presets, text cleanup and regex rules, and optional cached audio export for mobile playback.
Uses Google Gemini AI to rewrite selected Anki text for natural speech, then generates audio with voice, model and processing-mode controls, smart caching and no external dependencies.
Adds automatic text-to-speech playback and assigns TTS tags to selected fields per note type, without editing templates, supporting batch processing and language-specific voices.
Generates local AI text-to-speech audio from selected text or notes using downloadable voices in about 25 languages, with playback and bulk saving to cards.
Generates free text-to-speech audio with EdgeTTS and offline engines, saving files to cards or streaming during review, with batch generation, voice mapping rules and resumable checkpoints.
Function: It allows TTS playback of local audio generated by Kokoro.
1. Kokoro-FastAPI Service: https://github.com/remsky/Kokoro-FastAPI
2. Addon Configuration:
Unlike other operating systems that have built-in TTS engines, Linux can only achieve TTS by downloading audio files from cloud services through addons, such as:
I primarily study on Linux and frequently encounter issues with these solutions, including:
This has often been a painful experience. Recently, after encountering Kokoro, I explored this solution. It's essentially a modification of gTTS, replacing its original audio download process from Google Translate with local service requests to Kokoro-FastAPI. This resolves the issues of high latency and network interruptions, and incidentally, also solves the profile-switching problem.
这是一个anki扩展
作用是让 tts 播放 Kokoro 生成的本地音频
准备好 Kokoro-FastAPI 服务 https://github.com/remsky/Kokoro-FastAPI
扩展配置
Linux不像其他操作系统有内置的TTS引擎，所以只能通过扩展从云服务下载音频文件来实现TTS，比如：
我平时主要在Linux上学习，使用这些的方案，经常会碰到的问题是：
所以常常是苦不堪言，最近接触到 Kokoro 后，才探索出这个方案，其实就是基于 gTTS 修改，将其原来从 Google Translate 下载音频的部分换成从 Kokoro-FastAPI 的本地服务，解决了高延迟和网络中断的问题，顺便把切换用户的问题也解决了。
This is an Anki addon.
Function: It allows TTS playback of local audio generated by Kokoro.
1. Kokoro-FastAPI Service: https://github.com/remsky/Kokoro-FastAPI
2. Addon Configuration:
Unlike other operating systems that have built-in TTS engines, Linux can only achieve TTS by downloading audio files from cloud services through addons, such as:
I primarily study on Linux and frequently encounter issues with these solutions, including:
This has often been a painful experience. Recently, after encountering Kokoro, I explored this solution. It's essentially a modification of gTTS, replacing its original audio download process from Google Translate with local service requests to Kokoro-FastAPI. This resolves the issues of high latency and network interruptions, and incidentally, also solves the profile-switching problem.
这是一个anki扩展
作用是让 tts 播放 Kokoro 生成的本地音频
准备好 Kokoro-FastAPI 服务 https://github.com/remsky/Kokoro-FastAPI
扩展配置
Linux不像其他操作系统有内置的TTS引擎，所以只能通过扩展从云服务下载音频文件来实现TTS，比如：
我平时主要在Linux上学习，使用这些的方案，经常会碰到的问题是：
所以常常是苦不堪言，最近接触到 Kokoro 后，才探索出这个方案，其实就是基于 gTTS 修改，将其原来从 Google Translate 下载音频的部分换成从 Kokoro-FastAPI 的本地服务，解决了高延迟和网络中断的问题，顺便把切换用户的问题也解决了。