Jellypod Docs
Voiceovers

Voiceovers

Turn documents and images into narrated videos while preserving the supplied visuals.

Voiceovers turns documents and images into narrated Videos. Jellypod writes and voices the narration, then times each supplied visual to the finished audio. Voiceovers appear in their own Studio collection.

Features

  • Document and image input: Upload presentations, PDFs, and images, or reuse existing files from your Asset Library, as the authoritative visuals for the Video.
  • Speaker notes as context: Speaker notes in an uploaded .pptx inform that slide's narration.
  • Characters and Voices: Choose the Character and Voice that narrate the result.
  • Multilingual Creation: Choose the narration language independently from the Voice's Dominant language.
  • Script and Narration Editing: Revise narration and regenerate the affected audio.
  • Narration-aware framing: A document page can first appear in context, then focus on a readable graph, figure, table, or section while the narration discusses it.
  • Visual Editing: Reframe one supplied visual, regenerate it, or replace it with uploaded media.
  • Pronunciation Guide: Apply workspace-wide pronunciation rules without leaving the editor.
  • Web Research: Jellypod searches the web for background on your slides by default, unless your direction says not to.
  • Music, captions, watermark, and motion: After creation, add background music or a watermark in the editor, turn word-synced captions on when useful, and optionally add a subtle zoom effect to supplied visuals.
  • Sharing and downloads: Render, share, and download the result through the shared Video editor.
  • Retry after a failure: Continue a generation that stopped, reusing the files you already uploaded.

Voiceover creation may frame a supplied page or an embedded figure so it stays readable in landscape video, but it does not redraw or replace your material. If a safe focus is unavailable, Jellypod shows the whole visual over a matching solid-color background. After creation, the shared editor lets you reframe one visual without changing its other appearances.

The creation flow has no Visual Style, Brand Kit, watermark, background music, or orientation choice, and the result is always landscape. In the editor, you can explicitly change a visual, add background music, add a watermark, or turn captions on.

Create a Voiceover for supported files, limits, duration, captions, and editing behavior.

Was this page helpful?

On this page

Ready to create your podcast?

Go from idea to published episode in minutes. No recording, editing, or experience required.

Pricing on your terms

Pick the plan that works best for you

Pricing details

Start Podcasting

Publish your first episode in minutes

Open the Studio