Creating Voiceovers

Voiceovers are Videos built from documents and images you already have. Jellypod writes the narration, generates the audio, and times every supplied visual to the finished script.

Create a Voiceover

1. Open Home or Voiceovers in the studio sidebar. On Home, select Voiceover in the composer.
2. Choose one to four Characters, a narration language, and set a duration. Language starts from the Dominant language of the first Character's Voice, then falls back to your browser, region, and English; see Choosing a Duration.
3. Add up to 10 documents or images: drag and drop them onto the composer, click + to browse, or pick existing files from your Asset Library. Uploaded and picked files share the same 10-file cap. Each file can be up to 100 MB, with no more than 50 resulting visuals.
4. Optionally, add direction for the audience, tone, or key points.
5. Click Generate.

Generation narrates the whole script with the first Character you chose. To split narration across your other selected Characters, reassign individual paragraphs to them afterward in the editor; see Edit Narration and Visuals.

Generate is available as soon as you add a file. Jellypod finishes processing it in the background rather than making you wait, so a file that is still uploading or processing when you click Generate simply continues once generation starts. If a file fails to process, the Voiceover fails with that file's specific error instead of blocking Generate up front.

Jellypod takes you to Voiceovers while generation continues in the background. If you start there, the composer clears and the new card appears in the library below. The card shows its current status. If generation fails, a Retry generation button appears and reuses the files you already uploaded. See When a Video, Short, or Voiceover Fails. When it is ready, click the card to open the standard Video editor.

Files you upload become reusable Sources and appear in the Asset Library. They remain the authoritative visuals for the Voiceover created from them.

Supported Files

• Documents: PDF, PowerPoint (.ppt, .pptx, .pptm), Keynote (.key), and OpenDocument Presentation (.odp)
• Images: PNG, JPEG, and WebP

Pages inside a document stay together and keep their original order. Jellypod can arrange separate documents and images into an initial sequence.

Jellypod frames each visual around the narration. It can show a complete page for context, then return to a readable graph, figure, table, or section from that page when the narration discusses it. When a document contains the original graph or figure as a separate image, Jellypod can show that image without the surrounding page. It keeps captions, labels, and legends with the content they explain.

Jellypod never redraws or replaces supplied material during this automatic framing. If a focused crop could remove important content, it shows the whole visual over a matching solid-color background instead.

Speaker Notes

PowerPoint decks often carry speaker notes, the text you wrote to be spoken rather than shown. When you upload a .pptx, Jellypod reads the notes on each slide and uses them as context for that slide's narration, alongside the slide itself. There is nothing to turn on, and a deck without notes behaves exactly as it did before.

Jellypod treats notes as intent rather than a script to read out. It narrates their substance in the Voiceover's own voice and drops the stage directions, such as timing cues or a reminder to ask the room a question. Your direction still outranks both the slides and the notes.

Notes only survive in the PowerPoint format. A .pptx export from Google Slides keeps them, a PDF export does not, and notes in Keynote, OpenDocument, and legacy .ppt files are not read.

What a Voiceover Leaves Out

Because your files are the visuals, Voiceover creation skips several choices that Magic Video and Shorts offer. There is no Visual Style, orientation control (Voiceovers are always landscape), Brand Kit, watermark, or background music in the creation flow. After generation, the shared editor lets you add background music or a watermark, but it does not apply a Brand Kit or switch the Visual Style.

Generating a Voiceover costs 1 credit per second of narration. Your uploaded pages are the visuals, so nothing is generated for them and nothing is charged for them; see Understanding Credits.

Web Research

Jellypod searches the web for background on your slides by default, so the narration is not limited to what your files show. It skips the search when your direction tells it not to, which always wins, or when the slides plus its own knowledge already cover the deck well, as with generic, personal, or internal content.

The search only adds background: the narration never contradicts a slide, never states a figure your files do not support, and never mentions that a search happened. There is no separate toggle for this; to turn it off for one Voiceover, add direction asking Jellypod not to search the web.

Choosing a Duration

Duration defaults to Auto, which lets the narration's length follow your uploaded content instead of targeting a fixed runtime. Pick a fixed target from 3 to 60 minutes instead and Jellypod fits the narration to it. Every plan includes fixed targets up to 10 minutes; longer targets depend on your plan, up to 20 minutes on Starter and Educator, 30 minutes on Creator, and 60 minutes on Business. Auto also respects your plan: its narration stays under three quarters of your plan's Voiceover limit. Because Auto's final length is not known in advance, its credit cost is only set once generation finishes; see Understanding Credits.

Visual Motion

Visuals stay still by default, so uploaded slides and documents stay easy to read. Turn on Zoom effect in the settings menu next to the duration selector to add a subtle zoom in and out to each visual instead.

Captions

Captions are off by default for a Voiceover, since your uploaded slides and documents often already show the text on screen. Turn on Captions in the settings menu next to the duration selector to overlay word-synced captions on the narration. You can change this choice anytime afterward from the Captions button in the Video editor.

Edit and Share

A Voiceover uses the same editor as Magic Video and Shorts. You can revise the narration, regenerate audio, reframe a supplied visual, explicitly regenerate or replace an individual visual, review automatic timing, render a new version, download it, and share it. See Edit Narration and Visuals for the complete workflow.

Voiceovers have their own library in the sidebar, so they do not appear in the general Videos library. They may still appear alongside your other work under Recent creations.

Frequently Asked Questions

What file types can I upload?

PDF, PowerPoint, Keynote, OpenDocument Presentation, PNG, JPEG, and WebP. You can upload new files or pick existing ones from your Asset Library, up to 10 files total, with a 100 MB limit per file and no more than 50 resulting visuals.

How does Jellypod order my visuals?

Pages inside each document stay together and keep their original order. Jellypod can arrange separate documents and images into an initial sequence.

Do I have to wait for my files to finish processing before I can click Generate?

No. Generate is available as soon as you add a file. If a file is still uploading, Jellypod waits for the upload to finish and then submits automatically; processing continues in the background either way. If a file fails to process, the Voiceover fails with that file's specific error, and you can retry from its card without re-uploading.

What is the difference between a Voiceover and a Video?

A Voiceover uses visuals you already have and frames them around the narration without redrawing or replacing them. A Video generates its visuals for you, shot by shot, from your prompt and chosen visual style.

Can a Voiceover use more than one Character?

Yes, up to four. Generation narrates the whole script with the first Character you chose; reassign individual paragraphs to your other Characters afterward in the editor.

How long can a Voiceover be?

Duration defaults to Auto, which sizes the narration to your uploaded content and stays under three quarters of your plan's Voiceover limit. Fixed targets run from 3 to 60 minutes: every plan includes targets up to 10 minutes, the Starter and Educator plans unlock up to 20 minutes, the Creator plan up to 30 minutes, and the Business plan up to 60 minutes.

Can I choose a visual style, orientation, or background music for a Voiceover?

Voiceover creation has no Visual Style or orientation choice, and the result is always landscape. It also omits Brand Kit, watermark, and background music controls during creation. After generation, you can add background music or a watermark in the shared editor, but you cannot apply a Brand Kit or switch the Visual Style.

Does Jellypod use my speaker notes?

Yes, for PowerPoint .pptx files. Speaker notes on a slide become context for that slide's narration, so the Voiceover reflects what you meant to say and not only what the slide shows. Export Google Slides as PowerPoint rather than PDF to keep them, since a PDF export has no notes.

Does the narration use information from outside my uploaded files?

Yes, by default. Jellypod searches the web for background that can improve the narration, unless your direction tells it not to or the slides already cover the topic well. The deck stays the source of truth: the narration never contradicts a slide or states a figure your files do not support.

Can I edit the result?

Yes. Voiceovers use the standard Video editor. For a supplied visual, choose Reframe to reposition it, adjust its crop and zoom, show the whole visual, or restore Jellypod's automatic framing.

Do my visuals move or stay still?

Visuals are static by default. Turn on Zoom effect in the settings menu, next to the duration selector, to add a subtle zoom in and out to each visual.

Does a Voiceover include captions?

Not unless you turn them on. Voiceovers default to no captions, since uploaded slides and documents often already show the text on screen. Turn on Captions in the settings menu next to the duration selector, or toggle them afterward from the Captions button in the Video editor.

Can I create a Voiceover from the Voiceovers page?

Yes. The Voiceovers page has the same Voiceover composer as the studio dashboard, followed by your Voiceovers library.