Spotify announced in May 2026 that users can now create and import AI-generated personal audio into the Spotify app using a new command-line interface (CLI) tool currently in beta.
The feature works alongside existing AI coding and agent tools — specifically OpenAI’s Codex, Anthropic’s Claude Code, and OpenClaw. Users can prompt one of these agents to generate a podcast on a chosen topic, then use Spotify’s CLI tool to save it directly to their Spotify library. Spotify provided an example prompt: “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.”
Once imported, the podcasts appear in the user’s personal library and are not visible or accessible to other Spotify users. Users also receive a direct link to their podcast listing. To get started, users can visit the tool’s GitHub page and follow the setup instructions, which include logging in to a Spotify account through a browser.
Spotify cited growing user demand as the reason behind the launch. “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 said in a blog post.
Apps such as Google’s NotebookLM, Hero, and Adobe Acrobat have offered AI podcast generation from documents and other source material for several years. Spotify’s move may position it as a destination for this type of content rather than a creation platform, since the new tool relies on third-party AI agents to produce the audio.
Source: TechCrunch