What is Supertone?
Supertone is an AI audio tech startup that specializes in expressive singing/speech synthesis, original voice design, and speech enhancement. It offers proprietary technology that creates hyperrealistic and expressive results for music, video, and gaming content. Supertone's suite of tools enables creators to break content creation limitations. It also has capabilities for voice cloning, voice design, and speech enhancement. Its various products include the Voice Gene Designer, the Voice Content Creator, the Real-Time Voice Converter, and the Real-Time Voice Separator. Its Singing Voice Synthesis (SVS) and Controllable Voice Conversion (CVC) technologies also allow for a wide range of voice manipulation.
What is the Voice Gene Designer feature in Supertone?
The Voice Gene Designer feature in Supertone allows for the cloning of existing voices, creation of completely novel voices, or recommendation of the best matched voice for a character's appearance. This feature aids creators in voice-based content creation by offering a wide range of voice options and controls.
How does the Voice Content Creator in Supertone work?
The Voice Content Creator in Supertone is an all-in-one workstation that employs Voice Genes for the creation of singing and dialogue content. It provides a high level of control of independent elements of vocal expression, enabling creators to fine-tune their content's vocal components based on preferences and requirements.
What is the Real-Time Voice Converter feature of Supertone?
Supertone's Real-Time Voice Converter is a real-time voice conversion software with realistic quality. It allows virtual artists to interact directly with their fans and create entirely novel interactive content. This feature leverages cutting-edge voice conversion technology to deliver high-quality audio experiences.
How does Supertone's Real-Time Voice Separator work?
Supertone's Real-Time Voice Separator is an audio plugin that enables users to cleanly separate their voice from any noisy and reverberant environment in real time. This technology is particularly beneficial in scenarios where background noises can interfere with the clarity and quality of the vocal content.
What is the Singing Voice Synthesis (SVS) AI technology in Supertone?
Singing Voice Synthesis (SVS) AI technology in Supertone brings life to a new voice. It can be trained on melody and lyrics to sing, or on scripts and delivery to act. Through a workflow similar to DAW's and text editors, users can create the voice they want with full control.
Can Supertone's technology be used in gaming content?
Yes, Supertone's technology can be used for gaming content. It can be applied in character design, voice dubbing, and universe creation. The Voice Gene Designer can even recommend the best matched voice for a character's appearance, making the integration of voices in a gaming environment seamless and efficient.
What exactly can the Controllable Voice Conversion (CVC) in Supertone do?
The Controllable Voice Conversion (CVC) in Supertone allows the conversion of any voice to a voice of the user’s choice. It can be utilized not only to transfer the timbre of one’s voice but also to fine-tune its gender or age. This functionality opens up numerous possibilities for voice manipulation in content creation.
What awards has Supertone won?
Supertone has won the CES 2022 Innovation Awards Honoree: Software & Mobile Apps, and the NeurIPS 2021 among other honors. These recognitions underscore the innovation and effectiveness of Supertone's technology in the realm of voice synthesis and content creation.
Can Supertone be used in video content production?
Yes, Supertone can be used in video content production. It provides the ability to create any voice, which allows for limitless scenario choices. Its voice separation technology can completely separate an actor’s voice from any ambient noise in on-site recordings. Post-production alterations to a voice’s age, gender, diction, or delivery are all possible, as well as natural multi-language dubbing for global distribution.
Is it possible to do live performances or broadcasting with Supertone?
Yes, it is possible to do live performances or broadcasting with Supertone. The company's real-time AI technology allows for live broadcasting and performances, adding a new dimension of flexibility and interactivity to content creation and delivery.
How can Supertone assist in voice dubbing for games?
Supertone can drastically simplify the process of voice dubbing for games. Its face-to-voice matching AI technology can assist in finding and designing voices for characters, even potential to increase character popularity with a more unique voice. It removes the complications related to dubbing and ADR that can slow down global release schedules.
Can Supertone be used to create voices for a brand's identity?
Yes, Supertone can be used to create a voice that embodies a brand's identity. With Supertone's technology, you can find or create the perfect voice for your brand. This new voice can completely replace any preexisting voices and is everlasting.
How does Supertone handle data and privacy?
Supertone handles data and privacy with utmost care. It does not monetize on a voice without the permission of its rightful owner. The access to training and synthesized voice data is minimized, and marking technology is in place to detect AI-generated audio. Supertone ensures the respectful resolution of issues related to personal information through the use of new voices.
Can Supertone clone any voice?
Supertone has the capability to clone existing voices. However, it does not monetize a voice without the permission of its rightful owner. Supertone's Voice Gene Designer feature enables the cloning of a voice, creating unique or replicated vocal elements for content creation.
Can Supertone be used for text-to-speech synthesis?
Yes, Supertone can be used for text-to-speech synthesis. Its advanced AI technology can convert written text into realistic, expressive speech, making it an excellent tool for creating voiceovers, audiobooks, and any other spoken content.
What is Grapheme-to-Phoneme functionality in Supertone?
Supertone's Grapheme-to-Phoneme functionality is part of its text-to-speech synthesis technology. This capability enables the conversion of written language units (graphemes) into the corresponding units of sound (phonemes), facilitating accurate and natural speech synthesis.
Does Supertone provide real-time voice separation in a noisy environment?
Yes, Supertone does provide real-time voice separation in a noisy environment. This is made possible through its Real-Time Voice Separator feature, an audio plugin that enables users to separate their voice cleanly from any noisy and reverberant environment in real-time.
Can I use my own voice with Supertone's technology?
Yes, you can use your own voice with Supertone's technology. The Controllable Voice Conversion (CVC) technology allows for any voice, including your own, to be converted to a voice of your choosing. This can be used to transfer the timbre of your voice to another, and even fine-tune its gender or age.
What are the areas of research Supertone is involved in?
Supertone is involved in various areas of research such as Singing Voice Synthesis (SVS), Text-To-Speech synthesis, Grapheme-To-Phoneme functionality, Melody/Lyrics transcription, studio-quality speech enhancement, voice conversion, Natural Language Processing, Speaker Verification, and Automatic Speech Recognition. These areas allow Supertone to innovate in the content production landscape through technology.