Welcome!

Emotions

TL;DR; You can change the tone of a specific slide by adding an inline emotion tag at the top of its speaker notes, like [[cheerful]] Welcome to the course. The narrator stays the same — only the mood of that passage changes. This works with Standard voices that support styles; not every voice has every emotion.

Picking a single narrator for a video is the right starting point, but sometimes a particular slide needs a different feel. The congratulations slide should sound warm. The compliance warning should sound serious. The CTA at the end should sound upbeat.

Inline emotion tags are how you do that without switching voices mid-video.

How to use an emotion tag

Open your PowerPoint's speaker notes for the slide you want to change. At the very beginning of the notes — before the first word of narration — type a double-bracketed tag with the name of the emotion:

[[cheerful]] Welcome to our universe, a vast and wondrous place full of mysteries and surprises.

The tag controls the tone for that slide's narration. The next slide's notes revert to the default tone unless you add another tag.

A few important rules:

  • Put the tag at the start of the notes. Lupo reads it as a directive, not as text to narrate. It won't appear in the audio.
  • One tag per slide. Don't try to chain tags mid-sentence; the narrator won't interpret it the way you expect.
  • Emotions are voice-specific. Not every voice supports every emotion. If a voice doesn't have the one you asked for, Lupo falls back to the default tone for that slide.

PowerPoint slide with speaker notes showing an inline emotion tag at the top

The common emotions

These are the emotions you'll use most. They work with most English Standard voices and map to well-known neural voice styles:

  • cheerful — upbeat and warm. Good for welcomes, congratulations, and positive CTAs.
  • friendly — conversational and approachable. The default feel for most training.
  • excited — higher energy. Good for product reveals and announcements.
  • hopeful — gentle and forward-looking. Good for vision statements.
  • sad — slower and softer. Rarely appropriate for training, but useful in storytelling.
  • serious — lower and measured. Good for compliance warnings and anything consequential.
  • empathetic — calm and understanding. Good for sensitive topics like HR conversations or customer service.
  • customerservice — polite and professional. Designed for service-scenario content.
  • chat — casual and informal. Designed for explainer-style narration.

Different voices may support additional styles. If you want to experiment, start with these and expand from there.

When to use emotions (and when not to)

Use them when:

  • A specific slide genuinely needs a different tone to land.
  • You're telling a story across slides and one "beat" needs a mood shift.
  • You're producing a higher-production-value piece where flat narration would feel off.

Don't overdo it. An emotion tag on every slide makes the video feel theatrical and the narrator sound unstable. The baseline should be "no tag, default tone," with emotions used sparingly — maybe on 10–20% of the slides in a typical deck.

Troubleshooting

The tag is showing up in the narration. You probably used a single bracket ([cheerful]) instead of double brackets ([[cheerful]]). The double brackets are the marker.

Nothing changed. The voice you picked may not support that emotion. Try switching to a different voice or a different emotion that's more widely supported (like cheerful or friendly).

The emotion is too strong. Pick a milder one (friendly instead of cheerful, for example) or remove the tag entirely and let the default tone handle it.

Where to go next

  • Narrators — pick the base voice before layering emotions on top.
  • Premium Narrators — for content where emotional range really matters, Premium voices handle it better.