Select the Text-based editing icon in the right panel.
Last updated on
Oct 27, 2025
Learn how to use the generated transcript to identify speakers and assign speaker labels.
Try it in the app
Identify and label speakers in video transcripts in a few simple steps.
When speakers are clearly identified in a transcript, finding specific quotes or sections from each speaker becomes much easier. This helps them make accurate edits, such as cutting, rearranging, or highlighting parts of the conversation without accidentally changing or deleting the wrong speaker’s words.
With the Text-based editing feature in Firefly video editor, transcripts are automatically generated with speaker labels based on detected voices. The editor identifies and assigns speakers, and you also have the flexibility to update or reassign speaker labels if needed.
Before you begin:
Create a new project and add a video file with dialogue to the timeline.
The generated transcript identifies each speaker and aligns their spoken dialogue with the corresponding text.
If you want to add a new speaker to a set of text in the transcript or correct it by assigning it to another speaker, you can highlight the text and select the Assign speaker icon.
Speaker labeling makes it easy to locate and remove specific segments of video frames tied to individual speakers directly from the timeline.
Turn text into art with Adobe Firefly
Create beautiful images and video clips from text prompts using generative AI.
