Tokyo, Japan (July 30, 2024)—AI continues to make inroads into the recording and live sound spaces, and now Tokyo-based music tech start-up Dreamtonics has introduced Vocoflex, a real-time, AI-powered voice creation and transformation plug-in.
Released variously in three bundles along with Dreamtronics’ Synthesizer V Studio Pro and a number of voice databases, Vocoflex is defined as a singing voice conversion (SVC) technology, according to the company. Users can reportedly train Vocoflex to create AI voice models with as little as 10 seconds of source audio, and then operate the model on their own local computer, reducing the time it takes to render new voices and effects.
Music Industry Support Grows for AI Guidelines
Intended for creative pursuits, the software can interpolate between multiple models to create entirely new voices, reportedly rendering in real-time so that, for example, a single performer can tap into several voices during one live performance using Vocoflex. For a more tactile experience, Vocoflex allows users to connect and map their MIDI controller’s buttons, knobs, or sliders to adjust their voice.
One of the dangers of SVC technology, however, is its potential to be used unethically to recreate others’ voices. With that in mind, Vocoflex requires ID verification through Dreamtonics’ KYC-service partner and incorporates “an advanced tamper-proof audio watermarking feature.” Said to be undetectable to the ear, the watermark 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 user’s consent—a practice prohibited by the plug-in’s usage terms.
