Voice-Swap is proud to introduce our new free VST plugin and custom model training feature. The ability to create your own voice model has been the biggest request we’ve had from our 200,000 users since our launch last year. We’ve also known since we started Voice-Swap that for this technology to transform how singers, artists, producers and engineers work with vocals, it had to meet them in the DAW. 

That’s why we’re launching them both at the same time and why we worked so hard to ensure your custom voice models are accessible not only inside the DAW but integrated into our web platform, our stem separation and vocal swapping tool Stem-Swap and our new API. Here’s how it all works. 

VST Plugin

The Voice-Swap plugin allows users to effortlessly transform vocal recordings within their Digital Audio Workstation (DAW). All you’ve got to do is select an artist from a drop-down menu of licensed voices, drag and drop your audio onto the plug, and within seconds, your new voice will be returned from the Voice-Swap servers. As usual with all things Voice-Swap, royalties are automatically generated for the original artist whose voice has been used, ensuring ethical and fair compensation. 

You can use the plugin to change your lead vocal, experiment with new voices, add new backing vocals, harmonies, vocal textures and more. What’s even more exciting is you can also use the plugin to share your own voice with your trusted collaborators, or access voices that are shared with you, privately and securely. Download the plugin here and watch the video below to see how it works. 

Custom Model Training and VST Integration

Today Voice-Swap is also introducing a custom model training feature. This allows users to create their own voice models, that can be shared privately with collaborators, producers, labels, band members and more, enabling them to access and use the user’s distinctive voice within the VST plugin. Simply enter the email address of the Voice-Swap user you want to share your new AI voice with and the model will instantly appear in their plugin once they log in. 

Once trained, their new voice will automatically be available in Voice-Swap’s existing web platform, its stem separation tool Stem-Swap, its free VST plugin and via API for third-party integrations. 

This groundbreaking feature makes working on vocals, songs, mixes and projects significantly faster and more efficient and also offers singers and songwriters around the world a brand-new way to collaborate. Private sharing also gives singers all the advantages and flexibility of AI voice technology while allowing them to maintain full control over who can utilise their voice model.

Soon, users will have the option of monetising their custom voice models on Voice-Swap – more on that later. Create your own custom AI voice model here and watch the video below on how to integrate it into your VST. 

Copyright Protections

We believe AI doesn’t have to be about scraping data without permission and widespread copyright infringement. There is a way we can take advantage of this revolutionary tech without exploiting artists and rightsholders. To ensure the highest standards of copyright protection, all custom voice model training data will soon be meticulously cross-referenced against BMAT’s extensive database of over 180 million audio fingerprints. This crucial step prevents unauthorised voices from being created, safeguarding the rights of vocal artists and is the first solution of its kind in the industry. Learn more about our BMAT integration here – coming soon to user model training.

Fairly Trained Certification

Voice-Swap's commitment to ethical AI practices has also earned the company the globally recognised Fairly Trained Certification. All Voice-Swap models, including its base model, have been verified, and approved by Fairly Trained, underscoring Voice-Swap’s dedication to responsible AI development.

Shaping the Future

Via our new VST plugin that meets artists, singers, producers and engineers in their DAW, our new custom model training feature and our recently launched API for enterprise voice solutions, Voice-Swap is continuing to push the boundaries of what’s possible with voice cloning technology. By paying our artists royalties for the use of their AI voice and allowing singers to choose who has access to their custom model via our VST, web platform and API, Voice-Swap is giving back control to artists, while shaping the future of creativity for music makers. 

Thank you for being part of our journey so far – you can download the VST plugin here and create your own voice model here.