PlayPlay lets you quickly remove specific parts of a video (hesitations, filler words, repetitions, etc.) directly from its automatically generated transcript - in addition to manual trimming and one-click silence removal.
Once your media is added to the screen:
-
Click the three dots (Actions) on the media you want to edit, then select Edit.
Note: Your file must contain audio to generate a transcript.
-
The Trim tab opens automatically: select the language spoken in your video, then click Generate Transcript.
-
Once the transcript is ready, play the video if needed to follow along, then remove the parts you no longer want by selecting the word, sentence, or full paragraph and clicking Remove.
Note: You can restore any removed section at any time by clicking "Restore".
-
To remove several occurrences of the same keyword at once, type it in the search bar above the transcript, then click Remove All.
-
After trimming, you can still fine-tune timings directly in the timeline by dragging the handles or removing parts manually.
-
Click Confirm in the top right when you’re done.
-
Nothing is permanent: anything you remove can be restored in a few clicks.
-
The transcript stays linked to the media used to generate it. You’ll find it in the screen where it was created, and in any other screen or project using that media.
-
If you apply audio cleanup to your media, a brand-new transcript will be generated automatically.
-
Edits made through the transcript always apply to entire words or blocks of text. Cutting half a word isn’t possible.
-
Automatic silence removal can be used at any time during trimming, even while the transcript is generating.
-
If your video is longer than 15 minutes, the full transcript will be generated. However, any part beyond the 15-minute per-screen limit will be hidden by default (but restorable in one click).
-
The transcript detects different speakers, ignores silences, and displays filler words as regular text.
-
Like any AI-generated transcript, it may contain small errors (misheard words, accents, noise) and automatically remove some hesitations. The best approach is to use it for bulk edits, then refine the result in the timeline if needed. Better audio quality leads to better results.