Localize. Narrate.
Present.
A powerful Python toolkit for presentation localization. Extract slides, translate visuals, generate voiceovers, and create videos—all powered by Google Gemini AI.
Features
Everything You Need
A complete toolkit for localizing presentations and generating multimedia content with AI.
PDF Extraction
Convert PDF presentations to high-quality images. Configurable DPI settings (150-300+) with PNG or JPG output formats.
Script Generation
Generate professional voiceover scripts from slides using AI. Context-aware narration with markdown formatting and timing cues.
Image Translation
Translate text in images to any target language. Powered by Google Gemini AI for accurate, context-aware translations.
Voice Synthesis
Generate natural voiceover audio from scripts. Six distinct voices available: Puck, Charon, Kore, Fenrir, Aoede, and Orus.
Video Generation
Combine translated slides and voiceover audio into polished videos. Configurable resolution up to 1920x1080.
Full Pipeline
One-command localization workflow. Extract, translate, and generate audio in a single step with essai localize.
Quick Start
Simple by Design
Get started in seconds. Set up your API key and start localizing presentations.
# Install the package $ pip install montaigne # Create .env file with your Gemini API key $ echo "GEMINI_API_KEY=your-api-key" > .env # Verify everything is set up correctly $ essai setup API key configured successfully
## SLIDE 1: Introduction **[Duration: ~45 seconds]** Welcome to this presentation on artificial intelligence and its applications in modern business. --- ## SLIDE 2: Key Benefits **[Duration: ~60 seconds]** Let's explore the three main benefits of AI adoption: automation, insights, and scalability. --- ## SLIDE 3: Case Study **[Duration: ~90 seconds]** Our research shows a 40% increase in productivity when AI tools are properly integrated.
CLI Reference
The essai Command
A powerful command-line interface for all your localization needs.
--dpi 200 for resolution, --format jpg for output format.
--input for PDF or image folder, --context for additional context.
--script for input file, --voice for voice selection (Puck, Charon, Kore, Fenrir, Aoede, Orus).
--input for image or folder, --lang for target language (default: French).
--pdf, --script, --lang.
The world is but a school of inquiry. The matter is not who shall hit the ring, but who shall make the best courses at it.
Examples
Common Workflows
See montaigne in action with these real-world examples.
# Extract slides from a PDF $ essai pdf presentation.pdf --dpi 200 Extracted 15 pages to ./presentation_pages/ # Generate a voiceover script from slides $ essai script --input presentation.pdf --context "AI workshop" Generated script saved to ./voiceover.md # Generate audio with a specific voice $ essai audio --script voiceover.md --voice Kore Generated 15 audio files in ./audio/ # Full localization in one command $ essai localize --pdf presentation.pdf --lang French Extracting PDF pages... Translating images to French... Generating audio... Localization complete!