Anki Add-on

Turn Note Text Into Ready-To-Review Audio

AnkiDeck TTS batches selected notes, synthesizes speech, and writes audio tags to your target field with transparent queue status.

Open Repository See Features

Core Features

Queue-First Processing

Process current or browser-selected notes in sequence with per-row state and progress visibility.

Provider Flexibility

Switch between DashScope, OpenAI, and ElevenLabs models depending on quality, cost, and language needs.

Safe Write Controls

Use overwrite and skip rules to avoid accidentally replacing existing audio in important decks.

Workflow

  1. Pick deck, note type, source field, and target field.
  2. Choose TTS provider, model, voice, and language mode.
  3. Run processing and monitor each row as audio is generated.

Project Status

English UI, queue per-row progress, and sequential batch processing are active in this version.