text-to-speech

To read markdown files aloud, this text-to-speech synthesis skill strips markdown formatting and converts text to spoken audio using Microsoft Edge TTS. It handles symbol conversion and chunks long content for playback within your VS Code environment.

Text-to-speech synthesis for accessibility vocalizes written documents and code into spoken audio. This enables vision-impaired users to hear text content and allows multitasking developers to listen to research papers or code documentation.

Edge TTS supports multiple languages and voice presets for reading text aloud. The skill manages voice selection natively via TypeScript WebSockets to vocalize your documents and code with different accents and languages.

You can export spoken text content as MP3 audio files. After the text-to-speech engine synthesizes the vocalized audio, you can save the spoken output locally for offline listening or sharing.

Long content needs chunking for text-to-speech playback to prevent synthesis errors and maintain stable audio streaming. The skill automatically splits long text into manageable segments before sending them to the TTS engine.