You can control how your narration sounds by adding pause and pronunciation markup directly to your content before generating your video.
Pictory automatically interprets these markup tags when creating your voiceover, allowing you to improve pronunciation of names, acronyms, and technical terms, or insert natural pauses into your narration. The markup itself is never displayed in captions or spoken aloud.
Where can I use markup?
Markup is supported in the following workflows:
Script Editor - Add markup directly in the Script Editor before generating your storyboard. E.g the flows for Text to Video, URL to Video, and Document to Video
PowerPoint to Video – Add markup to your speaker notes.
Add the tags in speaker notes.
Enable Use speaker notes for narration during import.
Tags added to slide titles or slide body text are not supported.
Supported markup tags
Pictory currently supports two markup tags.
1. Custom pronunciation
Use the <pronounce> tag to specify how a word should be spoken while keeping the original word visible in captions.
Syntax
<pronounce say="how it sounds">Word</pronounce>
Example
Welcome to <pronounce say="koo-ber-NET-eez">Kubernetes</pronounce> Essentials.
Result
Caption
Welcome to Kubernetes Essentials.
Voiceover
Welcome to koo-ber-NET-eez Essentials.
Tips
Write the
sayvalue exactly as you want it to sound.Use plain English spelling (for example, koo-ber-NET-eez ), not phonetic symbols.
Tag names and the
sayattribute are not case-sensitive.Both single (
') and double (") quotes are supported.
2. Add pauses
Use the <pause> tag to insert natural pauses into your narration.
Syntax
<pause>short</pause> <pause>medium</pause> <pause>long</pause>
You can also use:
<pause/>
or
<pause></pause>
Both create a medium pause.
Pause durations
Value | Duration |
| 0.5 seconds |
| 1.25 seconds |
| 2 seconds |
Example
Our load balancer keeps your services online. <pause>long</pause> Always.
The pause is added to the voiceover, while captions continue to display normally.
Combine pauses and pronunciations
You can use both tags together in the same narration.
Example
Today we'll look at <pronounce say="ess-ess-ell">SSL</pronounce> termination. <pause>medium</pause> Let's begin.
Pictory applies both the pronunciation and pause automatically during voice generation.
Using markup in PowerPoint
To use markup with PowerPoint uploads:
Add the markup tags to the speaker notes for each slide.
During import, enable Use speaker notes for narration.
Generate your video.
Note: Markup added to slide titles, slide body text, text boxes, or bullet points is ignored.
Using markup in the Script Editor
When creating a project from Script Editor:
Enter the markup directly into your script.
Keep each tag on the same line as the sentence it belongs to.
Generate your storyboard.
Pictory parses the markup while splitting your script into scenes and preserves the pronunciation or pause in the generated narration.
Important notes
Markup tags are removed from captions.
Markup tags are never spoken aloud.
Only the pronunciation or pause effect is applied.
If the
sayattribute is missing or empty, the word is spoken normally.If an invalid pause value is used, the tag is ignored, and no pause is added.
Limitations
Markup is not supported in:
PowerPoint slide body text
Scene text edited after a project has been created
AI Video Editor
Audio to Video
Video summerizer
Images to Video
Frequently asked questions
Will customers see the markup tags in captions?
No. The markup is removed before captions are generated. Only the original text is displayed.
Are the tags spoken aloud?
No. Pictory interprets the tags but never reads them as part of the narration.
Can I use phonetic symbols in the say attribute?
No. Simply spell the word the way you want it to sound using plain text.
Can I edit pauses and pronunciations after my project has been created?
Yes. After the project is created, you can use the built-in Pause and Pronunciation controls in the Video Editor to modify the narration.