Import NotebookLM audio as an editable episode

Import from NotebookLM turns a finished audio file into a draft episode with an editable script, voiced by two of your hosts. It works from any podcast in Podcasts and Episodes, and any audio file works, not only NotebookLM overviews. To publish a recording as-is instead, see which import option to use.

Choose what to bring into Jellypod

Importing an Audio Overview rebuilds its speech in your hosts' voices. Transcription can mishear names, words and speaker changes, so check the draft against the recording. The original voices, performance, music and sound effects are not preserved in the rebuilt narration. Upload Audio preserves the recording but publishes it immediately, with no draft review step.

The audio import does not transfer your notebook's source library, citations, notes, prompts, sharing permissions or Google account. Add the original material separately if you need it available as Jellypod sources. Your podcast details, hosts, website and distribution settings are set up in Jellypod; they are not imported from the notebook. Use only material you have permission to upload and publish, as explained in content ownership and rights.

Create a new episode from the same sources

Choose this path when you want a different explanation, audience or structure, rather than a transcription of the existing overview.

1. Keep copies of your original documents and notes, or their supported links. Check supported source types before uploading; a notebook share link does not replace its underlying documents.
2. Create your podcast and first episode. Add the material as sources, choose your hosts, set the duration and describe the audience and focus. For example: “Use only the attached lesson notes. Explain the three causes of the conflict for students preparing for tomorrow's seminar.”
3. Generate the episode. Jellypod writes a new script and starts narration; the result can differ from your NotebookLM overview. Generation uses credits.
4. Review the script and listen to the audio before publishing. Correct unsupported claims, names and pronunciation, then regenerate the affected narration.

Import an audio file

Download the Audio Overview first. Google's Audio Overview help explains the Download action. Jellypod's import accepts the audio file, rather than a notebook or Audio Overview share link.

1. Open Podcasts in the sidebar and select your podcast.
2. In Create New Episode, select Import from NotebookLM.
3. Choose a First Host and a Second Host. They default to the podcast's regular cast, and they must be different. The podcast needs at least two hosts.
4. Drag the audio file into the upload area, or click Browse Files.
5. Click Import Audio. Keep the dialog open while it uploads, transcribes and imports, because it cannot be closed mid-import.

When it finishes, the script editor opens on the new draft.

What import does

• Transcribes and separates speakers. Detected speakers map onto your two hosts in order of first appearance. No new hosts are created.
• More than two speakers. Extra speakers cycle back onto your two hosts. You can reassign any speech block in the script editor afterward.
• Ignores non-speech sounds. Sounds like [sighs] or [laughter] are dropped, so they never become a speaker or a stray line. To direct delivery, add audio tags after import.
• Starts audio generation. Narration begins right away in your hosts' voices and uses credits (see understanding credits). If you don't have enough, the script is still saved and you can generate audio from the editor later.
• Publishes nothing. The result is a draft until you publish it.

Edit the draft in the script editor: rewrite lines, fix names and regenerate segments.

Review, preview and publish

1. Compare the imported script with the original recording. Check names, quotations, factual details and which host speaks each block. Reassign blocks where speaker detection got them wrong. Import starts narration automatically, so your first edit may happen after audio generation has already begun.
2. After changing text or a host, regenerate the affected narration and listen again. Text edits do not replace saved audio by themselves. See regenerating individual segments.
3. Check the episode title, description and cover art. For a reviewer link before publication, create a draft render in Share. Draft sharing does not add the episode to RSS. Private podcasts have no external share link.
4. Publish the episode when the audio and metadata are ready. For a Public podcast, publication adds the episode to its website and RSS feed. Publishing within a Private podcast keeps it in the workspace and integrations, with no public website or RSS.
5. To reach Spotify, Apple Podcasts or YouTube, submit your public RSS feed on a plan that includes distribution. Each platform needs setup and approval. YouTube RSS receives audio and cover art; video needs a separate upload.

The import creates an editable Jellypod episode, not an editable copy of the original audio file. Changing the script changes the narration you generate in Jellypod; it does not alter the downloaded NotebookLM recording.

Limits

Files over 30 minutes or 250 MB are rejected, so trim them first. Enterprise has no plan cap on episode length.

Troubleshooting

• "Audio is too long": the file is over 30 minutes. Trim it and try again.
• "File too large": the file is over 250 MB. Use a smaller file.
• "Please upload an audio file": the file is not audio. Use MP3, WAV or M4A.
• "Episode script truncated": the audio ran past your plan's episode length, so the script was cut and an upgrade prompt opens. The truncated draft is still created.
• "We couldn't detect any speech in this audio": the file has no recognizable speech. Try a different file.
• Hosts unavailable or fewer than two: add at least two hosts to the podcast, or pick hosts that are still active.

Open Help & Support in the Studio sidebar to chat with the team, or email support@jellypod.com.