Anki Quick Text-to-Speech Insertion Software Free Premium Microsoft Natural Audio Unlimited Usage Quick and Convenient!

Anki Add-ons
1

image
image2067×1626 242 KB

Note: New Flet interface, clean and intuitive.
I’ve put in significant effort to completely rewrite the Anki-TTS project I started back in March. If you’re interested, feel free to download and try it out. This is a labor of love, now updated to version V2.0. Performance has seen major improvements, and new features have been added. After selecting text, double-clicking A and B generates distinct audio files for each, aiding language learning. This feature is one-of-a-kind globally. It can automatically copy audio files to the clipboard for easy addition to Anki, and also functions as a text-to-speech tool supporting dozens of languages and their respective dialects.
Download link: GitHub - msjsc001/Anki-TTS-Edge: Effortlessly add free, high-quality Microsoft Edge TTS audio to Anki cards via text selection or copy, featuring a customizable, multi-lingual UI. 免费、快捷地为 Anki 添加高质量微软 Edge 语音，支持划词/复制触发、界面定制和多语言显示。

Previous V1 version link: Anki Quick Text-to-Speech! Free Microsoft Voices for Your Learning!

Anki-TTS-Edge

中文文档

Anki-TTS-Edge is a free, high-quality voice generation tool powered by Microsoft Edge TTS. It quickly generates audio from selected text, supports dual-voice mode for generating audio with two different voices, and automatically copies the generated audio to clipboard for fast pasting into apps like Anki. It also serves as a convenient reading tool for language learning and article reading.
Completely rebuilt with Flet (Flutter) in v2.0, featuring a modern UI, smooth animations, and enhanced functionality.

:sparkles: Key Features

  • Modern UI: Rebuilt from scratch using Flet (Flutter) for a sleek, responsive, and material design experience.
  • Top-tier Voices: Access 300+ free Microsoft Edge Neural voices across multiple languages and regions.
  • Dual Voice Mode: “Dual Blue Dot” system allows quick switching or sequential generation of two different voices (e.g., Male/Female, US/UK accents).
  • History Management: Automatically saves generation history. Re-listen, copy, or delete audio records easily.
  • Smart Monitoring:
    • Clipboard Monitor: Automatically captures copied text and pops up for instant generation.
    • Selection Monitor: (Windows only) Genereate audio instantly by selecting text.
  • System Integration:
    • Tray Support: Minimize to system tray to keep your workspace clean.
    • Pin to Top: Keep the window always on top for easy access while studying.
  • Internationalization: Full support for English and Chinese (Simplified) interfaces with real-time switching.

:rocket: Installation & Running

Requirements

  • Python 3.8+
  • Windows (Recommended for full feature support like Selection Monitor)

Setup

  1. Clone the repository

    git clone https://github.com/msjsc001/Anki-TTS-Edge.git
cd Anki-TTS-Edge

  2. Install Dependencies

    pip install -r Anki-TTS-Flet/requirements.txt

    Note: If requirements.txt is missing, manually install:

    pip install flet edge-tts pygame pyperclip pystray pillow

  3. Run Application

    python Anki-TTS-Flet/main.py

Build EXE (Optional)

To build a standalone executable:

# Install PyInstaller in virtual environment
pip install pyinstaller

# Build command
.\.venv\Scripts\python.exe -m PyInstaller Anki-TTS-Flet/main.py --name "Anki-TTS-Edge" --icon "Anki-TTS-Flet/assets/icon.ico" --add-data "Anki-TTS-Flet/assets;assets" --collect-all edge_tts --hidden-import=pystray --hidden-import=PIL --hidden-import=pygame --noconsole --onefile --clean --noconfirm

The generated Anki-TTS-Edge.exe will be in the dist/ directory.

:open_file_folder: Project Structure

Anki-TTS-Edge/
├── Anki-TTS-Flet/       # Main compiled source code
│   ├── assets/          # Icons and translation files
│   ├── config/          # Configuration and settings
│   ├── core/            # Business logic (TTS, Clipboard, History)
│   ├── ui/              # Flet UI Views (Home, History, Settings)
│   ├── utils/           # Helpers
│   └── main.py          # Entry point
├── .gitignore           # Git ignore rules
└── README.md            # Documentation

:hammer_and_wrench: Usage Guide

  1. Select Voice: Use the dropdown menus to filter by Language and Region.
  2. Generate: Type or paste text, then click the Blue Dot to generate audio.
    • Left Dot: Uses “Language (Left)” settings.
    • Right Dot: Uses “Language (Right)” settings.
  3. Copy File: After generation (Green → Red dot), click the Red dot or use Ctrl+C to copy the audio file path (for pasting into Anki).
  4. History: Switch to the History tab to view and manage past generations.
  5. Settings: Customize theme (Dark/Light), behavior (Autoplay, Tray), and more in the Settings tab.

Made with :heart: for Language Learners

1 Like