Supertone

• Real-time voice changer (Shift) with 100+ voice presets

• De-noise / de-reverb voice separation plug-in (Clear)

• Dialogue matching (reverb & EQ matching) via “Air” tool

• Expressive TTS and speech synthesis via API / SDK

• Voice cloning (custom voice creation from a sample)

• Voice conversion (speech-to-speech) with low latency

• Noise & reverb removal in audio tracks

• Custom voice & brand voice design

• Multi-language support (English, Korean, Japanese, others)

• Plugin support (VST, AU, AAX) and cross-platform (Windows / macOS)

Supertone is an advanced AI voice technology platform built to empower creators, media producers, and developers with expressive, clean, and transformable voice experiences. At its core, Supertone delivers tools for voice conversion, noise and reverb removal, voice cloning, and text-to-speech, enabling users to produce professional voice content with consistency and creativity.

One of the flagship modules is Shift, a real-time voice changer that lets users instantly adopt a new voice persona. With Shift, you can select from over 100 voices and speak in a different voice live, with low latency and expressive nuance.  The tool supports parameter adjustments like pitch, emotion, and blend to fine-tune how the voice sounds.  It is intended for applications like streaming, voice acting, virtual characters, and content narration.

Another key module is Clear, a plug-in that performs de-noise and de-reverb separation. Clear isolates voice from ambient sounds and reverberations by providing control over “Voice,” “Ambience,” and “Reverb” knobs. It runs in real time and can be used inside DAWs (VST, AU, AAX) on Windows and macOS, supporting industry sample rates and even Apple Silicon. Supertone also offers Air, a reverb & EQ matching tool that helps seamless ADR (automated dialogue replacement) by replicating the ambient sound and EQ of existing dialogue clips to match new recordings.

Beyond these endpoints, Supertone provides a TTS / speech synthesis API, expressive voices for different emotional styles, and voice cloning capabilities (creating a new voice model from just a few seconds of audio). It supports real-time voice conversion (RTVC) so you can transform a live voice input into another voice in real time. The platform is designed to serve content creators, video/audio producers, dubbing and localization teams, virtual character creators, and brands wanting to design custom voice identities.

In its business model, Supertone offers Supertone Play, which provides freemium access (free tier with credits) and paid tiers for extended usage. For instance, Play gives 150 voice presets, voice cloning, TTS with usage quotas, and commercial licensing under paid plans. They also sell Clear as a one-time plug-in purchase (lifetime license).  Licensing controls include attribution, voice CAPTCHA to prevent misuse, and inaudible watermarking for traceability in generated voices.

Supertone was acquired by HYBE in 2022, bringing its AI voice technology into music, entertainment, and global media.  Its toolset is emerging as a powerhouse for expressive voice synthesis, seamless voice transformation, and creative voice identity design.

Share Your Experience: