New York-based speech synthesis software startup ElevenLabs has launched its latest AI development — Voice Isolator and an API to go with it. Voice Isolator is designed to extract background noise, leaving clear dialogue for film, podcast, and interview post-production. The Voice Isolator API lets developers integrate the new product into third-party applications. To use the technology, content is uploaded and processed by the Voice Isolator model, resulting in what the company claims is speech comparable in quality to that obtained in a recording studio. The app is described as “free, with some limitations.”

ElevenLabs Head of Design Ammaar Reshi shared a demo with VentureBeat showing the tool “removing the noise of a leaf blower to extract crystal clear speech of the speaker.”

The media outlet also performed some tests of its own, noting that “the tool was able to process the audio in a matter of seconds” and “removed the noises — from those associated with opening/closing of doors and banging on the table to clapping and moving of household items — in almost all cases and extracted clear speech, without any kind of distortion.”

While many use noise-canceling microphones to eliminate unwanted noise in the recording phase, that technology may not be accessible “especially to early-stage creators with limited resources,” which is where AI tools like Voice Isolator could be useful, VentureBeat writes.

“Voice Isolator’s ability to remove irregularly occurring background noise certainly makes it stand out from most other tools that only work with flat noises,” adds VB.

ElevenLabs also has a Voice Isolator API web page, and technical documentation for the API. A YouTube demo documents the API and Voice Isolator at work.

Neowin writes that the demo — illustrating the creation of a website created with Claude AI and audio pulled in from a YouTube video — showcased the efficiency of Claude 3.5 Sonnet, which from “just one detailed query, was able to generate the code for the web page.”

Founded in 2022 by former Google and Palantir employees, ElevenLabs has also released tools for voice cloning and sound effects creation.

AI voice manipulation is a very active category. In March, OpenAI announced a voice cloning AI model that is not yet in public release, and in April VentureBeat reported on rapid voice cloning from Resemble AI.

Other products, including Adobe Premiere, Adobe Podcast, CapCut and Descript also offer noise reduction capabilities, according to Maginative.