Tokyo-based developer Dreamtonics have announced the release of a new AI-powered plug-in that’s capable of transforming the sound of a vocalist in real time. Vocoflex comes with a range of built-in models, and also allows users to train their own, and implements tamper-proof, inaudible watermarking to deter users from using artists’ voices without their consent.
The company say that while developing the technology behind the plug-in, they discovered a way to interpolate between multiple voice models to create entirely new voices, as well as reducing the rendering latency enough to allow for real-time processing. Users are able to import voice samples into Vocoflex, where they are displayed as a visual curve constructed from a collection of dots, with each dot representing a piece of audio taken from the input file. It’s also a selection of onboard tools that make it possible to generate new voices from within the plug-in itself. Signals that pass through the plug-in can then be altered to match the imported or generated voices, and manipulated in real time using the graphical display, as well as being controlled via MIDI.
Using the plug-in, it's possible to change voices from male to female (or vice versa), create varied backing vocals from a lead track, write ideas and demos for artists using different voices and much more. As well as its natural-sounding applications, Vocoflex can also be used in a more experimental way, creating more extreme other-worldly voices.
Vocoflex allows users to transform voices in real-time using a simple visual interface.
Dreamtonics say that while Vocoflex and all its associated bundles are designed for creative applications, they understand the potential risks and ethical implications of its use beyond these intended purposes. The voice-morphing tool allows users to train their own AI voice models with as little as 10 seconds of source audio as well as operating the model on their own local computer — drastically reducing the time it takes to render new voices and effects.
To help prevent unauthorised usage, the plug-in requires ID verification through the company’s KYC-service partner and incorporates an advanced tamper-proof audio watermarking feature. Undetectable to the ear, the method embeds a user-unique license ID into the voice, enabling Dreamtonics to identify both the use of Vocoflex and the creator of the audio sample, deterring users from importing voice samples without the singer or users consent. A full set of terms and conditions of the plug-in’s use can be found on the company’s website.
Compatibility
Vocoflex is supported on PCs running Windows 11, and Macs running macOS 11 and higher. VST3, AU and AAX plug-in versions are available, and there’s also a standalone application.
Pricing & Availability
Vocoflex is available now, and is currently being offered at an introductory price of $159.20€154.54 until 31 August 2024, when it will increase to its full price of $199€193.17.
The company are also offering a selection of bundles that include their flagship Synthesizer V Studio Pro instrument and an assortment of Voice Bundles. More information can be found on their website.
