Present without a clicker. A speech model and a small embedding model on your laptop listen to what you're saying and move to the slide you've started talking about.
Markdown, one slide per section, separated by a line with ---. Use # for the title, ## for a subtitle, - for bullets, > for a quote. Add cue: lines with phrases you're likely to say; they help matching and aren't shown.
Say “next slide”, “previous slide” or “go back”, or “go to slide 4”. These always work, even with auto-advance off.
cue: lines with the phrases you naturally use when you reach that slide, like cue: let me show you a quick demo.Everything you say is filed under the slide that was showing, with the time spent on each. Copy it as Markdown for speaker notes or a write-up. It stays in this browser tab only.
With Whisper selected, audio never leaves the laptop. The Chrome speech service option is faster but sends audio to Google; it's there as a fallback for slower machines.