Podzy

Podzy reads newsletters straight from a Gmail label you create. You move the issues you care about into that label, and the tool pulls the text out of each one automatically. It's the feature that defines the product: a simple, clever way to tell the app exactly which emails you want turned into audio, without copy-pasting anything by hand.

The core of the tool is the script engine. Instead of reading a newsletter word for word, the AI rewrites it into something that sounds like a host talking, with a proper intro, a natural flow and a close. Listeners describe the output as lively rather than a flat read-through, and that rewrite is what separates it from a plain text-to-speech voice reading your inbox aloud.

Podzy hands you a clean script file, then pushes it to Google Drive in a single click so you can grab it from anywhere. The PDF is formatted to suit a text-to-speech app, so you can drop it straight into your reader of choice without reformatting. It's a small step that saves the fiddly part of moving text between apps.

The tool doesn't lock you into one voice. It writes the script and lets you pick the text-to-speech app, and the company highlights Speechify as its main partner. That means you can use the voice you already pay for, including the celebrity voice options Speechify offers, instead of switching tools to hear your newsletters read back.

Paid plans add control over how the script comes out, plus a history of everything you have generated so you can revisit an old episode without rebuilding it. Automatic script generation also handles new issues for you, so the pipeline keeps running as fresh newsletters land in your label.

Podzy's second version adds a mobile app with its own text-to-speech voice, which folds the writing and the listening into one place. If you'd rather not juggle a separate TTS tool, that update is the reason to watch the roadmap. Current users get access to it as part of the lifetime deal.