AnkiWeb addon 459148001
Generates multilingual audio explanations for language cards using ChatGPT 5.4 and the Qwen TTS voice model, supporting multiple audio clips such as Chinese and Japanese on one card.
Open on AnkiWeb Find alternatives
stale
No GitHub repository linked.
| Min Anki | Max Anki | Updated |
|---|---|---|
| 2.1.50 | 2.1.66+ | 2026-04-06 |
Loading…
Generates contextual written explanations and spoken audio for target words in sentence cards using OpenAI models and selectable TTS engines, with one-click or batch processing.
Explains topics, chats about study material, and generates basic, cloze, image-occlusion, and audio cards from notes, documents, and images, with free local text-to-speech.
Generates AI text, text-to-speech audio, and images for individual Anki fields or entire decks in bulk, using configurable prompts and multiple model providers.
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.
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.
Reads Anki card text aloud during review using Windows Microsoft text-to-speech voices, supporting multiple languages and voices for language learning and users with ADHD.
All the credit goes to https://ankiweb.net/shared/info/375742312 Main difference is using QWENTTS (setup needs to be done separately) https://github.com/QwenLM/Qwen3-TTS?tab=readme-ov-file#environment-setup
This version has updated access to chatgpt 5.4 over 4.5 previously used and better voice language model QWENlm
But I wanted to have some support for having multiple audio ie Chinese audio + Japanese audio in one card. I also wanted to take advantage of the newer chatgpt models along with the newer voice models