A few days ago, AI company ElevenLabs launched its latest tool called Voice Isolator, which helps you remove background noise and get clear dialogues. Now, the company has launched Voice Isolator API, which allows third-party developers to integrate Voice Isolator into their applications to develop new applications and services.
The company only issued a very brief statement announcing the API. It said that the API charges for 1,000 characters per minute of audio and that technical information can be found in the documentation. Along with the statement, the company also released a demonstration video.
The demo shows the creation of a website in Claude that can grab the audio from a user-provided YouTube video and then have Voice Isolator clean it up. The resulting website looks pretty good and is very easy for the user to use. There is a field for the YouTube link, a button to generate the cleaned audio, and then a button to play the audio. There is then an audio progress bar that shows how much of the clip is left.
Obviously, this use case is just a demo, but it’s up to third-party developers to find creative ways to use Voice Isolator in their own products. The demonstration also shows how good AI bots like Claude are getting at programming tasks. With just one detailed query, he 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 GPT-4o and Gemini 1.5 Pro in most benchmarks. Sonnet is the mid-range model that balances results and speed. Opus and Haiku are the larger and more feature-rich models respectively, but have not yet been released for Claude 3.5.
