Generate multiple episodes as a connected series

A series is two or more episodes generated as one batch. Each script builds on the one before it. You can review an outline first, or ask for several episodes in a single prompt. A prompt that does not explicitly ask for more than one still produces one episode, as described in How the Podcast Agent Works.

Review a series outline first

1. Open the podcast and click Generate a Multi-Episode Series below the Create New Episode chat input.
2. Describe the series and choose 2 to 8 episodes. The hosts, attached sources, Auto-publish and Include show notes apply to every episode. Changing the shared duration updates every episode, so set it first, then adjust exceptions on individual rows. The dialog defaults to 5 minutes per episode; a single episode defaults to 7.
3. Click Create Outline. Jellypod reads your sources and, for factual topics, can run one web search and read up to two pages before planning. To keep the plan to your material, say to use only the attached sources.
4. Review the ordered plan. Each row shows the title, prefixed "Ep. 1:", "Ep. 2:" and so on, and a one-sentence summary. Click Edit to change the detailed prompt, then Save to refresh the title and summary. You can also delete episodes or change one episode's duration. Edits stay in the dialog until you create the episodes, and the last remaining episode cannot be deleted.
5. Click Create Episodes. The button shows an estimated credit total.

Generate directly from a prompt

Jellypod generates several episodes without an outline review when your prompt clearly asks for more than one.

A broad single-episode request ("an episode covering X, Y, and Z") stays one episode, and so does any ambiguous request. If your prompt states a duration ("15 minute episodes"), it applies to each episode, not to the series total. For wording that works well, see Tips for Better Prompts.

How episodes build on each other

Research and sourcing start for every episode at once. Scripts are written in order: each writer receives the full previous script plus short summaries of older episodes, so names, facts and running threads stay consistent. Titles get an "Ep. N:" prefix.

An episode waiting on an earlier one shows Waiting for Episode N, where N is the episode it is waiting for. If an earlier script fails, or does not arrive after 90 minutes per earlier episode, later episodes stop instead of starting from a gap.

You land on the podcast page, where every episode appears in the list with live progress. Generation continues if you close the tab.

Limits

The 10-episode cap matches the 10 generations an organization can run at once. A batch needs one free slot per episode, so it is rejected if you already have generations running. If your prompt asks for more than 10, Jellypod tells you to request 10 or fewer before starting.

Cost and failures

Each episode is charged for narration at 30 credits per minute. See Understanding Credits. Show notes follow the Include show notes setting (see editing episode details).

If an episode fails, its held credits are released and it is not charged. Retry the failed episode from the podcast page. Episodes that stopped because of it are failed episodes too. See Episode Generation Failed for causes and fixes.