diff options
| author | Paul Buetow <paul@buetow.org> | 2025-07-16 23:24:39 +0300 |
|---|---|---|
| committer | Paul Buetow <paul@buetow.org> | 2025-07-16 23:24:39 +0300 |
| commit | b2b007699b2a42ed86970f59d597034679265e91 (patch) | |
| tree | 4c3167cdece1ee181f92bc1a14b0e17e00db7c0c /README.md | |
| parent | e2e75315e5e7c3eaccdc38881bd2fa669bb9dda5 (diff) | |
Remove Pixabay and Unsplash image search support
- Delete Pixabay and Unsplash implementation files
- Remove API key configuration for both services
- Update CLI and GUI to only support OpenAI DALL-E
- Update documentation to reflect OpenAI as sole image provider
- Fix tests to handle nil client in OpenAI implementation
- Simplify configuration examples
The application now exclusively uses OpenAI DALL-E for image generation,
providing AI-generated educational images with creative art styles.
🤖 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 | 26 |
1 files changed, 7 insertions, 19 deletions
@@ -14,9 +14,7 @@ It has mainly been vibe coded using Claude Code CLI. - 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) +- Image generation: - **OpenAI DALL-E**: AI-generated educational images with random art styles (requires API key) - Batch processing of multiple words - Anki-compatible CSV export with translations @@ -61,9 +59,9 @@ export OPENAI_API_KEY="sk-..." totalrecall ябълка ``` -2. Use free Pixabay for images: +2. Generate with specific DALL-E model: ```bash - totalrecall ябълка --image-api pixabay + totalrecall ябълка --openai-image-model dall-e-3 ``` 3. Process multiple words from a file: @@ -96,9 +94,7 @@ audio: cache_dir: "./.audio_cache" image: - provider: openai # Image provider (pixabay, unsplash, or openai) - default: openai - pixabay_key: "" # Optional API key for higher limits - unsplash_key: "" # Required for Unsplash + provider: openai # Image provider (currently only openai is supported) # OpenAI DALL-E settings openai_model: "dall-e-2" # Model: dall-e-2 or dall-e-3 @@ -131,7 +127,7 @@ totalrecall [word] [flags] - `--skip-audio`: Skip audio generation - `--skip-images`: Skip image download - `--images-per-word int`: Number of images per word (default 1) -- `--image-api string`: Image source - pixabay, unsplash, or openai (default "openai") +- `--image-api string`: Image source - currently only openai is supported (default "openai") - `--all-voices`: Generate audio in all available OpenAI voices (creates 11 files per word) #### Audio Options @@ -150,14 +146,6 @@ totalrecall [word] [flags] ## API Keys -### Pixabay -- Optional - works without key but with lower rate limits -- Get your key at: https://pixabay.com/api/docs/ - -### Unsplash -- Required for Unsplash searches -- Get your key at: https://unsplash.com/developers - ### OpenAI - Required for both OpenAI TTS audio and DALL-E image generation - Get your key at: https://platform.openai.com/api-keys @@ -253,8 +241,8 @@ Available Bulgarian voices: - **DALL-E 3 Images**: ~$0.04 per image (standard), ~$0.08 (HD) - Both services cache results to avoid regenerating identical content -### Free Alternatives -- **Images**: Use Pixabay without API key (limited rate) +### Cost Savings +- Both audio and images are cached to avoid regenerating identical content ### OpenAI Troubleshooting - Check the API key has proper permissions enabled |