v1.2.2

Full Changelog: v1.2.1...v1.2.2

v1.2.1

• Fixed where no dependencies where installing with pip

Full Changelog: v1.2.0...v1.2.1

v1.2.0

🚀 Local-NotebookLM Release v1.2.0

Major Features

• 🖥️ Added Gradio Web UI for easy no-code usage
• 🔄 Improved pipeline stability and error handling
• 🎛️ Enhanced configuration options with more flexibility
• 📱 Responsive design for mobile and desktop access

Improvements

• 🌟 New intuitive web interface with drag-and-drop PDF upload
• 🎮 Interactive controls for format, style, and length selection
• 🔊 Live audio preview in the browser
• 📊 Real-time progress tracking during generation
• 🔧 Simplified configuration through the UI
• 🌐 Network sharing capability with --share option

Usage Examples

# Launch the web UI locally
python -m local_notebooklm.web_ui

# Share the web UI on your network
python -m local_notebooklm.web_ui --share

# Use a custom port
python -m local_notebooklm.web_ui --port 8080

Note: The web UI makes Local-NotebookLM accessible to users without technical knowledge while maintaining all the powerful customization options! 🎯

Now you can convert your PDFs to engaging audio content with just a few clicks! 🎙️

Best,
Gökdeniz Gülmez

What's Changed

What's Changed

Full Changelog: 1.1.2...v1.2.0

1.1.2

• Fixed the language support for Step 3

Full Changelog: v1.1.1...1.1.2

v1.1.1

🚀 Local-NotebookLM Release v1.1.1

Major Features

• 👥 Added multi-speaker support with panel discussion and debate formats (3, 4, or 5 speakers)
• 🌍 Implemented multiple language support via new language parameter
• 🎙️ Enhanced voice configuration with additional speaker options
• 🧠 Improved prompting for more reliable and stable results

Improvements

• ⚡️ Added callback mechanism in Step 3 to automatically fix incorrect format generation
• 📊 More progress bars for clearer status reporting during processing
• 🔧 Renamed voice configuration fields for better clarity:
  • Co-Host-Speaker-Voice → Co-Host-Speaker-1-Voice
  • Added Co-Host-Speaker-2-Voice, Co-Host-Speaker-3-Voice, Co-Host-Speaker-4-Voice
• 🛠️ Enhanced error handling and recovery from generation errors

Usage Examples

# Multi-speaker format
python -m local_notebooklm.start --pdf documents/paper.pdf --format panel-discussion

# Language support
python -m local_notebooklm.start --pdf documents/paper.pdf --language german

Note: When using non-English languages, ensure your LLM and TTS models support your target language! 🌐

Now you can create even more dynamic and diverse podcasts with multiple speakers in various languages! 🎙️

Best,
Gökdeniz Gülmez

What's Changed

Full Changelog: v1.1.0...v1.1.1

v1.1.0

🚀 Local-NotebookLM Release v1.1.0

Major Features

• 👥 Added multi-speaker support with panel discussion and debate formats (3, 4, or 5 speakers)
• 🌍 Implemented multiple language support via new language parameter
• 🎙️ Enhanced voice configuration with additional speaker options
• 🧠 Improved prompting for more reliable and stable results

Improvements

• ⚡️ Added callback mechanism in Step 3 to automatically fix incorrect format generation
• 📊 More progress bars for clearer status reporting during processing
• 🔧 Renamed voice configuration fields for better clarity:
  • Co-Host-Speaker-Voice → Co-Host-Speaker-1-Voice
  • Added Co-Host-Speaker-2-Voice, Co-Host-Speaker-3-Voice, Co-Host-Speaker-4-Voice
• 🛠️ Enhanced error handling and recovery from generation errors

Usage Examples

# Multi-speaker format
python -m local_notebooklm.start --pdf documents/paper.pdf --format panel-discussion

# Language support
python -m local_notebooklm.start --pdf documents/paper.pdf --language german

Note: When using non-English languages, ensure your LLM and TTS models support your target language! 🌐

Now you can create even more dynamic and diverse podcasts with multiple speakers in various languages! 🎙️

Best,
Gökdeniz Gülmez

What's Changed

• v1.1.0 by @Goekdeniz-Guelmez in #6
  Full Changelog: v1.0.2...v1.1.0

v1.0.2

v1.0.2

Full Changelog: v1.0.1...v1.0.2

v1.0.1

Full Changelog: v1.0.0...v1.0.1

v1.0.0

🚀 Local -NotebookLM Release v1.0.0

Major Features

• ✨ Added more audio styles, formats, and customizable lengths
• 👥 Implemented dynamic single and two-speaker content creation
• 🧠 Enhanced prompting for existing styles with better context retention
• 🔌 Added support for new providers: Google Gen AI, Anthropic, ElevenLabs
• 🛠️ Major stability improvements across the pipeline
• ⚙️ Users can now add custom system prompts (needs to be added in the config.json file)

Improvements

• 🎭 More voice options and character profiles for realistic podcasts
• ⚡️ Better error handling and recovery mechanisms
• 🔧 Optimized memory usage during processing
• 📊 Enhanced configuration options for fine-tuning output
• 🚀 Performance improvements during processing

Now you can create even more diverse and professional-sounding podcasts with expanded AI capabilities! 🎙️

best,
Gökdeniz Gülmez

New Contributors

• @flamby made their first contribution in #2

Full Changelog: v0.5.2...v1.0.0

v0.5.2

🚀 Release v0.5.2

Improvements

• ✨ Added chunking for large inputs to prevent API token limits
• 🔧 Configurable chunk size via chunk_token_limit parameter
• ⚡️ Better handling of rate limits with automatic delays
• 🧠 Smarter transcript processing for multi-part content
• 🛠️ Fixed "Request too large" errors when processing big files

Now your podcast generation works smoothly with files of any size! 🎙️

best,
Gökdeniz Gülmez

Full Changelog: v0.5.1...v0.5.2