HomeGame GuidesElevenLabs is launching the Voice Isolator API so that it can be...

ElevenLabs is launching the Voice Isolator API so that it can be used in third-party apps

Published on

A few days ago, the AI ​​company ElevenLabs launched its latest tool called Sound insulator allowing you to remove background noise, leaving you with clear dialogue. Now, the company has launched the Voice Isolator APIenabling third-party developers to integrate Voice Isolator into their own applications to invent new applications and services.

The company only released a very brief statement to announce the API, saying that the API is charged at 1,000 characters per minute of audio and that technical information can be found at the documentation. It also released a demo video with the statement.

The demo shows creating a website in the cloud that can extract the audio from a user-supplied YouTube video and then clean up the audio with Voice Isolator. The resulting site looks pretty good and is very simple for the user to interact with, there is a YouTube link box, a button to produce the cleaned audio and then a button to play the audio back. Then there is an audio progress bar to see how much of the clip is left.

Obviously, this use case is just a demo, but it will be up to third-party developers to find creative ways to use Voice Isolator in their products. Inadvertently, the demo also shows how good AI bots like Claude are becoming at programming tasks, with just one detailed query, it was able to generate the code for the web page.

The Claude model used in the demo was the latest Claude 3.5 Sonnet model which outperformed both the GPT-4o and the Gemini 1.5 Pro in most metrics. Sonnet is the mid-powered model that balances results with speed. Opus and Echo are the bigger and bigger models respectively, but they haven’t been released for Cloud 3.5 yet.

Latest articles

More like this