diff options
| author | Paul Buetow <paul@buetow.org> | 2025-07-15 23:42:32 +0300 |
|---|---|---|
| committer | Paul Buetow <paul@buetow.org> | 2025-07-15 23:42:32 +0300 |
| commit | b105333c061ea165b3b79317415cbb8b9cfb7c75 (patch) | |
| tree | c2682cc156c372d85ab52d514df4316ceda9071d /README.md | |
| parent | 61529facc2c5321de9f0ab9123cb1de25bcab62c (diff) | |
feat: add English translations and detailed attribution files
- Automatic Bulgarian to English translation for all words
- Save translations to separate _translation.txt files
- Include translations in Anki CSV export
- Add detailed attribution files for audio and images:
- Audio: model, voice, speed, instructions, processed text
- Image: model, size, quality, style, full prompt used
- Expand image styles to 42 different options (including superhero comic, yoga, etc.)
- Improve image prompts to strongly avoid text generation
- Fix image overwrite issue - now overwrites existing files instead of failing
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 15 |
1 files changed, 14 insertions, 1 deletions
@@ -11,12 +11,15 @@ It has mainly been vibe coded using Claude Code CLI. - Audio generation using **OpenAI TTS**: High-quality, natural-sounding voices (requires API key) - Random voice selection by default for variety - Option to generate in all 11 available voices +- Automatic Bulgarian to English translation + - Saves translations to separate text files + - Includes translations in Anki CSV export - Image search and generation: - **Pixabay**: Free stock photo search (optional API key) - **Unsplash**: High-quality photo search (requires API key) - **OpenAI DALL-E**: AI-generated educational images with random art styles (requires API key) - Batch processing of multiple words -- Anki-compatible CSV export +- Anki-compatible CSV export with translations - Configurable voice variants and speech speed - Support for WAV and MP3 audio formats - Audio and image caching to save API costs @@ -206,6 +209,16 @@ Create a text file with one Bulgarian word per line: вода ``` +### Output Files +For each word, the tool generates: +- `word.mp3` - Audio pronunciation (random voice) +- `word_translation.txt` - English translation +- `word_1.jpg`, `word_2.jpg`, etc. - Generated images +- `anki_import.csv` - Anki import file (when using --anki flag) + +With `--all-voices` flag: +- `word_alloy.mp3`, `word_nova.mp3`, etc. - Audio in all 11 voices + ## Anki Import 1. Generate materials with the `--anki` flag |