Product updates

Jellypod now has two new board-style explainers, Chalkboard and Blueprint, plus a clearer, more focused Whiteboard Explainer.

Chalkboard draws each idea in textured white chalk on a near-black canvas. It has the familiar feel of a classroom explanation, with light handwritten captions that stay easy to read.

Blueprint uses white and pale-cyan drafting lines on deep blue. A stationary grid sits behind the drawing, giving diagrams, systems, and process explainers a more technical look without adding clutter.

Board scenes are easier to follow

All three board styles now stay focused on the idea that matters most. Comparisons remain in one scene when you need to see the relationship, while busy explanations break into clearer steps.

Drawings follow the narration more naturally, give you time to take in each finished scene, and keep important artwork clear of captions.

Whiteboard is clearer and more focused

Whiteboard Explainer now keeps each scene focused on one object or idea at a time. The drawing is easier to follow from start to finish, with cleaner details that make the final illustration easier to understand.

The improvements work automatically in both shorts and videos. Pick Chalkboard, Blueprint, or Whiteboard Explainer when you choose a visual style. See Creating Shorts for the full style guide, or Creating Videos for the videos workflow.

You can now create videos, shorts, and voiceovers through the Jellypod API, and videos and shorts through the MCP connector, alongside podcasts.

Turn a training document into a narrated voiceover through the API, or ask your assistant to make a short explaining its key idea. Videos and shorts have their own endpoints and MCP tools, matching the choices in Studio; voiceovers remain an API and Studio product. Both interfaces can discover the available settings, start generation, check progress, and retrieve a download. Failed generations remain failed over MCP; the public API retains its retry endpoints.

File uploads go through the API or the Studio Asset Library. An assistant using MCP can pass a public webpage or YouTube URL, or plain text it already has, as research material, and can also send a finished script directly. Compatible MCP clients also show a product card with status and a preview when the output is ready.

Saved request keys help prevent duplicate generation when a response is lost. Existing podcast integrations can keep their current requests, with optional idempotency keys available for episode generation.

Open Developers for JavaScript, Python, and cURL examples. The product API guide covers the endpoints, and the agent guide explains how to use them through HTTP or MCP.

Voiceovers now read the speaker notes in your PowerPoint decks.

Upload a .pptx and Jellypod pulls the notes off each slide and uses them as context when it writes that slide's narration. Notes are usually the closest thing a deck has to a script: what the chart is actually showing, why the slide is there, the number behind the bullet. None of that is readable from the slide image alone, which is all a narrator had to work from before.

Jellypod treats notes as intent rather than a script to read out. It narrates their substance in the voiceover's own voice and skips the parts written for the presenter instead of the audience, such as timing cues or a reminder to ask the room a question. Direction you add at creation still outranks both the slides and the notes.

There is nothing to turn on. A deck without notes behaves exactly as it did before, and so does a deck where only some slides carry them.

Speaker notes only survive in the .pptx format. A .pptx export from Google Slides keeps them, a PDF export does not, so export as .pptx when your notes matter. Voiceover accepts PDF and .pptx files; export Keynote, OpenDocument, and other presentation formats to one of those first.

This works in the studio and in the Slides to Podcast and PowerPoint to Video tools.

Read more in Voiceovers.

Credits are now charged when Jellypod generates something, not when you render, publish, or download.

Before you generate a short, video, voiceover, or podcast episode, Jellypod estimates the cost from the duration you picked and the audio, images, and video clips it will create. That number sits next to the Generate button. Click it for a breakdown of how credits work.

When generation starts, Jellypod reserves that many credits so two generations cannot spend the same balance. When it finishes, the charge settles to what was made: 1 credit per 2 seconds of audio, 7 credits per generated image, and 20 credits per generated video clip. If a generation fails, the hold is released and you are not charged.

Rendering, publishing, scheduling, and downloading are free. Edit the timeline, switch templates, and export as often as you like.

For example, a 30 second short shows an estimate of about 65 credits with a still-image style, or 155 with animated clips, and settles to the exact count once the visuals are in.

Read more in Understanding Credits. For what that means next to an agency's price tag, see how much an explainer video actually costs made either way.

Captions no longer have to match your short or video's visual style.

Click Captions in the editor to open a gallery of every caption look Jellypod offers, from Retro Comics' bold word-by-word highlighting to the clean Whiteboard treatment, each with a live preview of real words appearing on screen. Pick one to turn captions on in that look, or choose No Captions to turn them off. A new short, video, or voiceover still starts with the caption look linked to its visual style, so nothing changes until you open Captions and pick something else.

See Managing Videos for the full walkthrough, or Managing Shorts for shorts.

My Characters now has the same search-and-filter bar as the Voice Library, so a growing roster stays easy to work with.

Type a name, a line from a backstory, or a word that describes the voice, such as "British" or "documentary," and the table narrows to characters that match. A search always checks your whole roster, so it still finds a character even while a filter is set.

The Filters button holds a Gender filter. Below the search bar, a Language dropdown and an Accent dropdown appear once your characters span more than one, and chips for Voice clones, Designed, and Library narrow by how a character's voice was made. A control that would not change your list, because every character shares that trait, stays out of the way.

The Language and Accent dropdowns open with their own search box, so you can type a name instead of scrolling, and the option you have picked keeps a check mark beside it.

We've added Full Screen Captions, a new Podcast Template that makes the transcript the entire visual.

Each word appears when it is spoken and stays on screen until the current caption page is complete. Then the next phrase starts on a clean frame. There is no cover art or waveform competing with the words.

The template uses your selected background color and font, and it works in landscape, portrait, and square layouts. It is a strong fit for episode videos and social clips that need to read clearly before someone turns on the sound.

How to use it

1. Open an episode in the Studio.
2. Click Video Style above the video preview.
3. Pick Full Screen Captions, then click Use.

The preview updates immediately, with no visual generation required. See Video Templates for the full Podcast Template lineup.

Episode pages now play audio through the same controls as your embed player, in the Studio and on your podcast website.

Opening a published audio episode in the Studio used to show no player at all until a video was ready. Now it plays inline with cover art, play/pause, adjustable speed, skip back 10 seconds or forward 30, volume, and a progress bar. On your podcast website, episode pages get the same upgrade in place of the browser's plain audio bar, matching your site's theme in light and dark mode.

Sharing also no longer requires a video: any published episode with a render, audio or video, gets a working share link. See Sharing Episodes and Your Podcast Website for details.

We just added 178 new professional voices to the Voice Library, including our first voices in eight languages: Arabic, Hindi, Greek, Czech, Danish, Norwegian, Finnish, and Filipino.

Accents got deeper too, 20 of them new in this release. Italian now comes in Sicilian, Milanese, Venetian, and Romanesco. French adds Quebec, Chinese splits into Beijing and Taiwan Mandarin, and Arabic ships in both Egyptian and Modern Standard. Even English picked up Boston, New York, and Southern US voices. All told, the library now holds nearly 400 voices across 22 languages and more than 50 accents.

This matters most when your audience does not listen in English. A voice whose primary language matches your listeners sounds native to them, not translated, so pick the voice made for the language and accent your audience speaks.

To browse the new arrivals, open Voices in Studio, then filter by language or accent. The Voice Library guide covers searching, previewing, and favoriting if you want the full walkthrough.

Your colors and logos now live in one place. A brand kit holds five color roles (Primary, Secondary, Accent, Background, and Text) plus separate logos for light and dark backgrounds, and it belongs to your organization rather than to a single podcast.

The fastest way to make one is to paste your website URL. Jellypod reads the site for your brand name, logos, and colors, then opens the editor pre-filled with what it found. You review and correct every value, and nothing saves until you confirm it.

Assign a kit to a podcast and its website picks up the accent right away. Edit the kit later and the site follows. New shorts start from your organization default, and you can switch kits or turn branding off for a single short before generating.

Each Video Style shows a badge for how much of a kit it uses: Full for the whole palette, Accent for the accent color only, or None for styles that keep their own look. Generated video snapshots your kit at generation time, so recoloring a brand kit never rewrites a short you already made.

Click Brand Kits under Personalize in the studio sidebar to set up your first one. Full walkthrough in Brand Kits.