I am nearly at the end of medical school so it is time I publish and "advertise" my open source scripts/apps for anki!
I’m excited to share [Voice2Anki](https://github.com/thiswillbeyourgithub/Voice2Anki), a tool I’ve been developing that combines the power of LLMs (like ChatGPT) and TTS models (like OpenAI’s Whisper) to create high-quality Anki flashcards from voice recordings. It’s designed to be fast, flexible, and language-agnostic, making it a powerful tool for anyone who uses Anki for learning or memorization.
As a medical student, I needed a way to create large volumes of high-quality flashcards quickly. Traditional methods were time-consuming, so I built Voice2Anki to automate the process. It’s been a game-changer for me, and I believe it has significant potential for anyone who relies on spaced repetition systems like Anki.
### Key Features
- Universal Language Support: Works seamlessly in any language.
- Adaptive Learning (Few-Shot Learning): Learns from your corrections to improve future cards.
This is a free and open-source project, and I’d love to see it grow. If you’re a developer interested in helping improve the CLI version, integrate it as an Anki addon, or contribute in any other way, your expertise would be hugely appreciated.
### Explore My Other Projects
I’ve built several other tools to enhance Anki workflows:
I am nearly at the end of medical school so it is time I publish and "advertise" my open source scripts/apps for anki!
I’m excited to share [Voice2Anki](https://github.com/thiswillbeyourgithub/Voice2Anki), a tool I’ve been developing that combines the power of LLMs (like ChatGPT) and TTS models (like OpenAI’s Whisper) to create high-quality Anki flashcards from voice recordings. It’s designed to be fast, flexible, and language-agnostic, making it a powerful tool for anyone who uses Anki for learning or memorization.
This project is part of a larger suite of tools I’ve been building to enhance Anki workflows. You can explore more in [AnkiAIUtils](https://github.com/thiswillbeyourgithub/AnkiAIUtils).
### Why I Built This
As a medical student, I needed a way to create large volumes of high-quality flashcards quickly. Traditional methods were time-consuming, so I built Voice2Anki to automate the process. It’s been a game-changer for me, and I believe it has significant potential for anyone who relies on spaced repetition systems like Anki.
### Key Features
- Universal Language Support: Works seamlessly in any language.
- Adaptive Learning (Few-Shot Learning): Learns from your corrections to improve future cards.
- Customization: Supports multiple LLMs (ChatGPT, GPT-4, Replicate, OpenRouter) and TTS models.
- Anki Integration: Automatically imports cards with tags, marks, and deck organization.
- Smart OCR: Processes images while preserving formatting.
### How It Works
1. Record your voice (e.g., speaking out flashcards).
2. Voice2Anki transcribes and corrects the text using LLMs.
3. It creates and imports the flashcards directly into Anki.
### Getting Started
Check out the [GitHub repository](https://github.com/thiswillbeyourgithub/Voice2Anki) for installation instructions and detailed documentation.
### Looking for Contributors
This is a free and open-source project, and I’d love to see it grow. If you’re a developer interested in helping improve the CLI version, integrate it as an Anki addon, or contribute in any other way, your expertise would be hugely appreciated.
### Explore My Other Projects
I’ve built several other tools to enhance Anki workflows:
- [Whisper Audio Splitter](https://github.com/thiswillbeyourgithub/whisper_audio_splitt...): Automatically splits long audio recordings into smaller segments.
- [OCR_with_format](https://github.com/thiswillbeyourgithub/OCR_with_format): OCR for Anki that preserves formatting.
- And more! Check out my [GitHub profile](https://github.com/thiswillbeyourgithub) for the full list.
I’d love to hear your feedback, suggestions, or questions. Let me know what you think!