Product Updates

You can now import a NotebookLM audio overview into Jellypod and rebuild it as an editable episode with your own hosts.

Open a podcast, click the upload icon next to Create New Episode, and choose Import from NotebookLM. Pick the two hosts you want, drop in the audio, and Jellypod transcribes it, separates the speakers, and creates a draft episode whose script you can edit line by line before generating audio in your hosts' voices. This is different from Upload Episode Audio, which publishes a recording as-is: Import from NotebookLM turns the audio back into a script you control.

It works with any audio file (NotebookLM is just the common starting point), up to 30 minutes. See Importing a NotebookLM Audio Overview for the full walkthrough.

Google shipped a major NotebookLM update of its own shortly after this feature launched. It didn't touch Audio Overviews, we broke down what actually changed.

The AI assistant you already use can now create podcasts in your Jellypod account with the new MCP Connector.

Connect Claude, ChatGPT, Cursor, or any MCP client to https://mcp.jellypod.com/mcp, sign in once, and your assistant works inside your account end to end: create a podcast and its hosts, drop in sources from a URL or pasted text, generate an episode, and publish it, all without leaving the chat. Ask Claude to "turn this article into a two-host episode and publish it to my morning show" and it happens in your account. Nothing publishes on its own, and live content can't be deleted by accident.

It's available to all users. See MCP Connector for the full setup walkthrough and the complete list of what your assistant can do.

The Jellypod Partner Program now pays 30% recurring commission for a year on every paid subscription you refer.

This is real revenue share, not a one-time credit. Refer someone who runs a training program, a course, or a newsroom, and once their team is paying you earn 30% of every invoice they pay Jellypod for their first 12 months as a customer.

How to apply

The program is application-gated. Apply at partners.dub.co/jellypod, or open the "Become a partner" card in the studio sidebar. Once you are approved, copy your unique partner link and start sharing, then track referred sign ups and payouts in the partner portal.

Commission is 30% of what each referred organization actually pays, for up to 12 months per customer. See the Referral Program docs for the full walkthrough.

Podcasts can now be generated via email. Automations now can have their own unique email address and anything sent is transformed into a podcast episode, generated from the email's content.

If you already write a newsletter or blog, email automations turn that content into a second channel without additional work. Set your automation's address as a new subscriber to your Substack, Ghost, or beehiiv, and every issue you send your readers also goes out as a podcast conversation to Spotify, Apple Podcasts, and YouTube.

Set up a new Automation in the sidebar, then send a newsletter to the provided email address. Full documentation here in Podcast Automations.

It is one of a few ways to trigger episode generation from tools you already use. See content marketing automation for the rest, including Zapier and n8n triggers from a broader marketing stack.

We've added a new video template called Conversation that puts your hosts on screen side by side.

It's a natural fit for multi-host shows. Each host gets their own avatar, and that avatar pulses whenever they are the one talking, so viewers can always tell who is speaking.

How to use it

1. Open an episode in the editor and find the video player controls.
2. Click Template Library and pick Conversation in the "Choose a template" dialog.
3. Click "Use Conversation" to apply it, then generate your video.

We've made Conversation the default template for new episodes, so multi-host videos use it out of the box. It pulls in the hosts who actually speak in your script and renders their avatars, so add a photo to each host to get the most out of it.

You can now customize your podcast's brand and background color.

This color will apply to the background of your generated video and sets the accent on your podcast website. If a specific episode needs its own color, you can override the podcast-level color just for that episode without touching the rest of the show.

How to use it

To set a podcast-wide color:

1. Go to the Podcast you'd like to edit.
2. Click through the "Edit Details" until the last step for "Additional Settings".
3. You'll see a Brand Color picker here. Drag the color wheel or type a hex value, and click "Save".

To edit the color per episode:

1. Open the episode you want to customize.
2. On the top navbar, next to the template and video orientation buttons, you'll see a new Color Picker.
3. Use that dropdown picker to set the episode color and click "Save as podcast default" to promote this color choice to the entire podcast, including future episodes.

If you don't manually choose a color, podcast episodes inherit the primary color from your cover art unless you override it.

You can now email someone a link to create a voice clone directly in your account, without them ever signing up for Jellypod.

Say you're producing an episode that needs your colleague as a subject matter expert. Invite them to record their voice as a Jellypod host, they upload a short sample from their phone, and a new host with their voice shows up in your library, ready to drop into the episode.

How to use it

1. On the Hosts page, click Create Voice Clone, select Invite a guest, and enter the guest's name and a short backstory.
2. Copy the invite link, or click Send email to deliver it from Jellypod.
3. Your guest opens the link, no Jellypod account required, and uploads or records voice samples directly.
4. When they submit, the new host lands on your Hosts page and you get an email letting you know it's ready.

Manage pending invites at Hosts → Invites: resend the email, copy the link again, or revoke it. Links are single-use and expire after 24 hours.

You can now import an externally-generated script, letting Jellypod match script speakers to your account's existing host voices. If a speaker cannot be matched to an existing host, Jellypod will intelligently create a new host with a suitable voice from our Voice Library.

Say you wrote a multi-host interview in ChatGPT or a Google Doc. Import the script to Jellypod and as long as you put an existing host name on each speaker's lines, Jellypod will match it correctly. Any names where Jellypod can't find a match and only exist in the script are created automatically with a fitting voice and a short backstory. No setup beforehand required.

How to use it

1. Open the Create Something New page and select Upload Existing Script.
2. Add your script. Paste it in, or upload a plain text, Markdown, Word (.docx, .doc), .rtf, .pages, or PDF file, up to 4 MB. Marking speakers in brackets like [Alex] gives the cleanest results, but plain prose works too - Jellypod detects who is speaking.
3. Review the preview. Every speaker it finds is listed, each tagged to show whether it matches an existing host or will be created as a new one.
4. Import. Jellypod matches speakers to your podcast's regular hosts first, then the rest of your account, and creates a new host for anyone left, picking a voice in the script's language and writing a backstory from their lines.
5. Audio generation starts automatically, the same as when the Podcast Agent writes a script from scratch. You don't need to click Generate Audio yourself.

Note: Newly created hosts don't impact your podcast's regular hosts and only apply for this specific episode. When this happens, a banner above the script editor will allow you to "Update Podcast" to sync your podcast's default cast to these hosts.

Your AI agent can now make podcasts for you.

We've shipped a Jellypod skill that teaches an agent how to use your Jellypod account end to end: design hosts, attach sources, draft the script, and render audio against the real Jellypod API.

Hand the agent a prompt like "spin up a weekly podcast that summarizes my company's product updates" and it picks the voices, builds the hosts, pulls in your sources, and produces the episode in your library.

The skill is open source. Install instructions for your agent of choice (Claude Code, Claude.ai, ChatGPT, and others) are in the repo: github.com/Jellypod-Inc/skills.

We just added 30 new voices to the Jellypod Voice Library.

They sound more natural, more expressive, and more flexible across different podcast styles. Some episodes need a calm narrator. Others need a sharper editorial voice, a warmer co-host, or a more energetic presenter who can keep the conversation moving.

To try them, create a new host or edit an existing one, choose Voice Library, and browse the first three pages. Give a few samples a listen, compare the delivery, and pick the voice that feels right for your next episode.

They are live now. Give them a try the next time you are casting a host.