We’ve previously covered some of the amazing (and groundbreaking) tools brought to artists by the creative team at lalal.ai — read more on that here: https://performermag.com/home-recording/how-ai-will-change-the-way-you-write-record-and-sample/
To recap what we thought at the time:
“One of the main selling points is that there’s no great quality loss in the separation, and for the most part that’s actually true (shock!). We processed acoustic singer/songwriter tracks as well as some more heavily arranged funk tracks and overall, and were pleasantly surprised and impressed with the ability for the AI to extract parts and separate audio with genuine clarity…I know other platforms have hit the market claiming to do something similar, but usually (at least from our experiences), they tended to be full of digital artifacts, audio ghosting and other anomalies that audibly reminded you of the other parts of the songs (doesn’t that kind of defeat the purpose?)…With some initial skepticism out of the way, we thoroughly enjoyed testing out the lalal.ai platform, and can see how this would be a useful tool across genres, for a multitude of reasons and use cases.”
Now they’re back with another potential game-changer, enter the…
AI VOICE CHANGER
Here’s what they say about it: “Use the power of AI to sing like Drake, Taylor Swift, SZA, and other artists. Select the voice pack and apply it to your recordings.” Learn more about it and give the free beta s shot today by heading here: https://www.lalal.ai/voice-changer/
So, how does it work?
Simple: you upload a track, either a fully mixed and ready-to-go edit, or just a vocal guide track, if you wish. The AI magic behind the scenes does its thing on their servers, and allows you to select a voice inspired by a popular artist to transform your song into…well, what can only be described as a new work that completely re-contextualizes the vocals with the selected artist pairing. It’s quite a stunning concept, to be sure.
While there are likely some kinks to work out during the beta phase, the algorithm is clearly pretty far along in development, so if you’ve ever wondered what the voice of an artist you’re producing would sound like in the style of another popular, contemporary artist, you can give it a shot. It changes the overall timbre, style, pitch and character of the voice and spits out the results the algorithm provides in a new audio track.
Getting started couldn’t be simpler — the online interface makes it pretty much idiot-proof. You click upload to select the track you wish to transform, then you select which voice pack to engage on the back-end for the AI’s algorithm to use. While it doesn’t work in real-time (at least not yet), you will get your resulting track and can hear how it sounds. Best results occur with the cleanest, highest quality input tracks, so make sure you’re uploading good-quality, high-bitrate and sample depth audio to begin with.
Got some ideas of your own, or represent an artist who might make a great voice pack? They’re even open to collabs on custom voice packs. Please contact their support team at [email protected] to engage in a conversation.
Have you tried the AI Voice Changer yet? Let us know what you think!