Spotify Opens Door to AI-Generated Podcasts via New CLI Tool

Users can now generate personal podcasts from documents, schedules, or articles and listen to them inside Spotify, but the process requires programming tools. The company announced a new command-line interface (CLI) tool, currently in beta, that works with existing AI coding agents like OpenAI’s Codex, Anthropic’s Claude Code, or OpenClaw.

“People are already starting to use their agents to create personal audio that guides their day: from summaries of class notes before an exam to briefings of what’s on their calendar. And they’re asking for a way to listen to it on Spotify, where they already listen to everything else,” the company stated in a blog post.

The feature builds on a trend already seen in apps like Google’s NotebookLM, Hero, and Adobe Acrobat, which let users turn existing material into podcast-style audio. Spotify’s version keeps the generated content private—the podcasts appear only in the user’s own library and are not shared with other Spotify users.

How to Use the New Tool

To get started, users must visit the tool’s GitHub page and follow the setup instructions. The process requires logging into a Spotify account through a browser. Once connected, a user can write a prompt—for example, “Build me an audio session that dives deep into the history of the World Cup with details about key players, where it’s been held, and what I should know about the games this year”—and the agent will generate a podcast and save it directly to Spotify. The system also provides a link to the podcast’s Spotify listing.

The generated podcasts are stored in the user’s Spotify library for on-demand playback, but remain inaccessible to other listeners on the platform.