What problem does it solve? Reading long documents on screen is slow and inaccessible for vision-impaired users or anyone multitasking. This Skill gives the AI assistant a voice, reading markdown files, code, and text aloud with natural neural voices directly inside VS Code. ## Core Features & Use Cases - Document Read-Aloud: Reads the current selection or entire document via keyboard shortcut (Ctrl+Alt+R), with smart markdown stripping that converts headings, tables, symbols, and emojis into natural speech. - Multi-Language Voice Synthesis: Auto-detects 32 languages and selects an appropriate neural voice, with four English voice presets (Default, Warm, British, Friendly). - MP3 Export & Long Content Handling: Saves any document as an MP3 file, chunks long documents with retry logic, and offers LLM-based summarization for content over 5 minutes. - Use Case: A developer proofreads a 30-minute design document by listening during a commute, or a vision-impaired user listens to research papers read aloud with automatic table-to-speech conversion. ## Quick Start Ask the assistant to read the current document aloud, or press Ctrl+Alt+R in VS Code to start playback through the webview audio player.
