Description
1. Advanced speech recognition and enhancement technology
VOXSORY uses advanced algorithms to process and clarify the voices of users with various voice disorders and characteristics. In the process, the voices of existing metaverses or virtual characters are improved to be more natural and understandable, contributing to enhanced user immersion. In particular, the voice recognition accuracy (WER of 15~18%) for impaired voices boasts global-level performance, which dramatically improves user experience.
2. Personalized voice enhancement
Provides customized voice enhancement based on the user's individual voice characteristics. By distinguishing between the character's voice and the user's voice and applying appropriate clarification techniques in real time, it provides clear and easily understandable speech in games and educational content while maintaining the character's speech patterns and emotional characteristics. This enables natural interaction between virtual characters and users.
3. Multi-platform compatibility
voxsory can be seamlessly applied across various platforms such as metaverse, games, education, IoT devices, etc. with the same performance. By optimizing the speech clarification and enhancement technology according to the characteristics of each platform, voxsory delivers excellent performance for characters in games, speech recognition in education platforms, voice output on IoT devices, etc.
4. Enhanced privacy and data security
We've added features to protect the privacy of voice files with an automatic modulation key generation system and multiple modulation techniques to keep user data secure. User voice data in the metaverse and virtual characters are processed with unique modulation keys to prevent external leakage and comply with privacy regulations. This allows users to use the service with peace of mind.
5. AI-based customized character voice generation
AI models can be utilized to generate voices that match the characteristics of each character, and the character's emotions and intonation can be changed in real time to make character dialog more lively. In games and metaverse environments, real-time interaction with users enhances immersion, and in educational content, a variety of characters make learning more fun.
Company Information
-
-
-
Category
TV Show,
Music,
Immersive Content,
CT,
Startup
-
Main Products
LUCY5, AI VOICE DNA
-
Main Markets
UNITED STATES
VIET NAM
MEXICO
JAPAN
INDONESIA
CHINA
-
Established
2019
-
Website
Visit Website
Braindeck is a company that create the finest AI Voice DNA. We are contributing to the expansion of IP profits of media & entertainment companies through conversation and singing models based on multilingual voice generation for virtual humans and characters, as well as conversation and singing through voice restoration of the deceased. Currently, we are focusing on developing intelligent conversation technology with persona and advanced deep voice detection technology to protect voice copyright, and are pioneering the global market through alliances with overseas partners such as the United States and Japan.
Category & Business Type
TV Show
Category : Producer, Online/Mobile Platform, Audiovisual Technology, Production/Content Creation, Technical Service, System/Software, Application Development
Business Type : Program Copyright Deals, Co-Production/Collaboration, Investment Attraction
Music
Business Type : Label, Agency, Distributor, Promoter, Producer, Musician/Composer/Lyricist, Cultureal Arts Institution and Assocation, Media
Main Business
o ENTERTECH, MUSIC TECH SOLUTION SALES( API, SDK)
- AI VOCAL GENERATION, MUSIC GENERATION, AI DUBBING
o PLATFORM BUSINESS