This app can add AI narration to any site or text – here's how to make it work

(Image credit: Shutterstock)

Artificial intelligence-powered audio creator ElevenLabs has brought its synthetic voices to the iPhone with a new iOS app. The ElevenLabs Reader App will read out any uploaded text or website using ElevenLabs' library of synthetic and cloned voices, even your own if you want.

The new app essentially turns books, website content, and any other text into a kind of podcast hosted by whichever voice you want to hear. Users can listen to content by pasting a link, copying text, uploading a file, or selecting one of the preloaded stories, which are then read in the chosen voice from the library. The stories are public domain and come from Project Gutenberg, including "Cinderella," "The Tale of Peter Rabbit," and "The Adventures of Sherlock Holmes."

As for the voices, users can pick based on accent, style, and tone to match the text. That might mean switching from a warm, friendly voice reading a bedtime story to a child to a brisk, authoritative voice reading a scientific study. The app can run in the background like an audiobook or podcast and is clearly aimed at those who are multitasking, at least based on the promotional video.

Narrate Your Life

The ElevenLabs Reader App only narrates in English for now and only in the U.S., Canada, and the UK. The company said it is "working on widening access, adding content download and audio sharing features, and adding all of the 29 languages available inElevenLabs'' wider library thanks to its multilingual AI model. The app is included with a subscription to ElevenLabs' platform, though you can get three months of free access without an account. An Android version is also coming soon, with an early access waitlist available to sign up for.

"It's our mission to make content accessible in any language and voice, and everything we do is oriented around achieving that mission," ElevenLabs head of growth Sam Sklar explained in a blog post about the new app."Creating best-in-class AI audio models is not enough. Creators need tools through which they can create. And consumers need interfaces through which they can consume audio."

See more Computing News

Eric Hal Schwartz is a freelance writer for TechRadar with more than 15 years of experience covering the intersection of the world and technology. For the last five years, he served as head writer for Voicebot.ai and was on the leading edge of reporting on generative AI and large language models. He's since become an expert on the products of generative AI models, such as OpenAI’s ChatGPT, Anthropic’s Claude, Google Gemini, and every other synthetic media tool. His experience runs the gamut of media, including print, digital, broadcast, and live events. Now, he's continuing to tell the stories people want and need to hear about the rapidly evolving AI space and its impact on their lives. Eric is based in New York City.