-
What's new
- New features
- Get started
-
Generate images with Text to Image
- Generate images using text prompts
- Customize generated images
- Generate images using 3D scenes
- Generate vectors
-
Work with audio and video
-
Work with audio
- Translate audio
- Frequently asked questions about Translate audio and Translate video
- Generate sound effects using text prompts
- Generate sound effects using your voice as a guide
- Writing effective text prompts for sound effects generation
- Fix pronunciation in the speech text
- Add pauses to the speech text
- Add tone to the speech text
- Remove noise and improve voice quality
- Frequently asked questions about Enhance Speech
- Generate soundtracks
- Generate speech from text
- Generate speech using partner models
- Supported languages in Generate Speech (beta)
- Generate soundtrack for an uploaded video
-
Work with video
- Translate video
- Generate videos using text prompts
- Generate videos using images
- Generate Video FAQ
- Writing effective text prompts for video generation
- Generate videos with virtual avatars
- Generate videos using partner models
- Best practices for writing content for Text to avatar
- Use video as composition reference
- Use style presets for video generation
- Enhance your prompt for video generation
- Match camera motion to reference video
- Generate videos with transparent backgrounds
-
Work with audio
-
View generated history
- View generation history
-
Work with enterprise features
- Collaborate using Style Kits
- Create object composites
-
Train custom models
- Custom models overview
- Train custom subject models
- Train custom style models
- Preview and test custom models
- Publish custom models
- Manage custom models
- Generate images using Custom Models
- Training essentials for custom models
- Training essentials for custom subject models
- Training essentials for custom style models
- Share custom models
- Share custom models for editing
- Share custom models for review
- Share custom models for use
- Custom model projects
- Manage custom model project access
- Custom models trained on Firefly Image Model 4
- Retrain your custom models
-
Creative Production
- Creative Production overview
- Remove or replace backgrounds on multiple images
- Crop multiple images simultaneously
- Color grade multiple images simultaneously
- Best practices for background removal in Creative Production
- Reframe multiple videos simultaneously
- Best practices for Reframe Videos in Creative Production
- Resize multiple images simultaneously
- Technical specifications for Creative Production preset workflows
- Create professional headshots in bulk
-
Share and download
- Share in the Firefly Community gallery
- Share and download your work
- Troubleshoot
-
Ideation and mood boarding
-
Firefly Boards
- About Firefly Boards
- Create boards
- Add artboards to the canvas
- Add images
- Remix images
- Add and edit texts
- Add and edit shapes
- Add comments
- Share for collaboration
- Partner models to generate images
- Edit images
- Add videos
- Generate image variations
- Collect, arrange, and align elements in canvas
- Work with linked documents
- Partner models to generate videos
- Use Boards Presets for complex workflows
- Generative text edit (beta)
-
Firefly Boards
-
Firefly video editor (Beta)
- About Firefly video editor
- Technical requirements
- Set up your project
- Add and organize media
- Work with timeline
- Work with transcript
- Finalize and export
- Keyboard shortcuts
- Troubleshoot
Text-based editing
تاريخ آخر تحديث
28 أكتوبر 2025
Learn about Text-based editing and how you can use it to edit your video by directly interacting with the transcript.
Text-based editing makes it easier to work with videos that have a lot of dialogue, such as interviews, documentaries, or podcast content. Instead of manually scrubbing through timelines or audio waveforms, you can edit your video by directly interacting with the transcript. This means you can cut, rearrange, or refine your footage by editing the text, making the process faster.
Key features of Text-based editing
- Auto-transcribe your footage: Automatically generate a transcript of your video, with dialogue aligned to timecodes. This makes it easy to search, navigate, and select clips directly from the transcript.
- Edit Using Text: Create rough cuts by selecting and rearranging text in the transcript. As you edit the text, the matching video clips are automatically trimmed and placed in the timeline.
- Fine-tune with precision: Once your rough cut is in the timeline, you can refine it further, such as trimming the clip or rearranging it with the spoken words.
- Clean up dialogue easily: Quickly detect and remove filler words like “uh” and “umm” in bulk. You can also filter and delete dialogue from specific speakers.