Abstract

A web article is split into segments, each segment is turned into a speakable version by rules or an AI model, synthesized by any speech engine and cached under a content hash. Slides are derived automatically from the article and advance in sync with the voice; the spoken block is highlighted and upcoming text is shown in light grey. Tables are summarized in speech, code is never read aloud, formulas are spoken in words. A phone operates the whole flow through a directional control element (button, gesture, voice, pen or remote) and can send the presentation to a separate display such as a TV via screen mirroring (AirPlay, Cast, Smart View, HDMI, smart-TV browser, projector). Any shape, colour or size of the control, any speech synthesis, language, platform (web, app, desktop) and content type (learning article, briefing, scientific text) is included.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.

Share

COinS