ShortslyBegin with finished audio
Upload a recorded segment or reuse a saved voiceover instead of recreating the delivery with text-to-speech.
Use cases
Turn podcast audio into visual short-form clips.
Choose a self-contained excerpt, upload the original recording, and add visual references for the people, places, products, or ideas being discussed.
- Choose a segment with its own setup, useful idea, and closing thought.
- Upload the original audio so the speaker’s delivery remains the timing source.
- Add photos, logos, or other references for the subjects mentioned in the clip.
Keep the original voice at the center.
Build visuals around meaning
Match scene changes, source media, and captions to the moments where the speaker changes subject or emphasis.
Edit the clip as a project
Refine the visuals, timing, captions, backgrounds, and sound effects without changing the original recording.
Cut the episode around one complete thought.
The original recording stays at the center while source images, generated scenes, and captions make the excerpt understandable on its own.
Step 1
Select a complete excerpt. Choose a passage with a clear setup, useful idea, and ending that works without the full episode.
Step 2
Upload the original audio. Keep the speaker’s delivery as the timing source instead of recreating it with text-to-speech.
Step 3
Add context and review. Upload references for the subjects discussed, then check captions, scene relevance, and pacing.
Questions about podcast clips.
Can I start with an existing podcast recording?
Yes. Upload the audio and use it as the timing source for the visual edit, captions, and scene changes.
Do I need video of the speakers?
No. You can use source photos, generated supporting scenes, captions, backgrounds, or a combination of those elements.
Can I correct captions after generation?
Yes. Caption words remain editable on the generated timeline before export.
