AnkiWeb
- Rating
- 14 (๐ 12 ยท ๐ 2)
- Updated
- 2025-02-13
- Anki versions
- 24.04~
- Description language
- en
AwesomeTTS-AI-Version(unofficial)
AnkiWeb addon 903988322
Generates Anki audio via a local Kokoro text-to-speech service and other OpenAI-compatible TTS models, supporting multiple languages.
Open on AnkiWeb GitHub Ask about alternatives
Maintenance
stale
- Last update or commit was 592 days before the snapshot (2025-02-16).
- The repository has 2 test files.
GitHub
- Repository
- siochannell/awesometts-ai-version-unofficial- ยท more by siochannell
- Stars
- โญ 14 ยท forks 0 ยท open issues 1
- Last commit
- 2025-02-16
- License
- GPL-3.0
- Languages
- Python, Shell, JavaScript
- Tests
- 2
Will it work on my Anki?
Version branches
| Min Anki | Max Anki | Updated |
|---|---|---|
| 2.1.50 | 24.04+ | 2025-02-13 |
History across monthly snapshots
Loadingโฆ
Similar addons
Adds speech to flashcards using premium and free text-to-speech services, with easy voice sampling, text-processing rules, Ogg support, and one-click editor audio insertion.
Provides text-to-speech for Anki 2.1 with on-the-fly generation, service testing, and ImTranslator support, but is unmaintained, has broken NeoSpeech, and should not be used.
Plays locally generated Kokoro TTS audio through Kokoro-FastAPI, configured with a URL and language-voice mappings, reducing Linux cloud TTS latency and network/profile restart issues.
Generates AI sentences for a vocabulary word, randomly cycling them during review so users memorize the word, not sentence context.
Provides Google Cloud and Microsoft Azure text-to-speech for flashcards but is unmaintained, incompatible with recent Anki, and suggests alternatives.
Provides paid API-key access to automated translation, transliteration, and text-to-speech in many languages, automatically adding audio, translations, or transliterations to new notes.
README
Introduction
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.
Addon Installation
Since the author of AwesomeTTS has stopped updating AwesomeTTS and has shifted to maintaining another project called HyperTTS, you can completely disable or remove the AwesomeTTS plugin from the Anki plugin page without any worries. Then, enter the plugin code 903988322 to install the AwesomeTTS-AI-Version (unofficial).
Model Download
After installing the plugin, you also need to download Kokoro's model using Docker locally. Enter one of the following two commands in the command line, then configure the plugin to access the Kokoro API address, which is default to http://localhost:8888/v1/audio/speech. Note that if you change the container's port, make sure to update the port number in the API address.
docker run -p 8888:8880 ghcr.io/remsky/kokoro-fastapi-cpu:v0.2.0 # CPU, or:
docker run --gpus all -p 8888:8880 ghcr.io/remsky/kokoro-fastapi-gpu:v0.2.0 #NVIDIA GPU
Here is a detailed tutorial for everyone
Cautionary Notes
- At present, Chinese and Japanese voice only supports generating English with Chinese and Japanese accents.
- If the following error occurs and voice generation is not possible, please check and troubleshoot the issues in the following order:
- Check if the Kokoro model is open in Docker Desktop
- Restart Anki and try generating with another Voice
OpenAI Compatible
Additionally, I've added OpenAI Compatible (OpenAI Interface Compatible) service, which means you can install other OpenAI compatible TTS models locally (such as openai-edge-tts) for tts service.
Be mindful that when using OpenAI Compatible, there may be instances where you've selected OpenAI Compatible, but the generated voice turns out to be Kokoro's. This is likely due to a caching issue; providing it with a new word to generate should refresh the cache.
License
AwesomeTTS-AI-Version-unofficial-: GPL-3.0 license anki-awesome-tts: GPL-3.0 license