Core AI Upgrades VoicePix With Advanced AI Audio Features

(RTTNews) - Core AI Holdings (CHAI), an AI-driven mobile games developer, on Thursday announced a major upgrade to VoicePix, its AI-powered music and voice generation platform, adding new features that make synthetic audio more realistic and easier for creators to use.

The VoicePix upgrade introduces several new features and enhancements, including AI voice cloning to create realistic voices for narration, dialogue, and music; text-to-music and lyric generation to make songs from text; custom voice avatars that let users create personalized voices from photos and recordings; and improved sharing tools for easy publishing and collaboration on social and content platforms.

VoicePix uses a proprietary Text-to-Speech (TTS) engine, now upgraded to version 2.0, which significantly improves voice realism, emotional expression, and control over speech patterns. Powered by advanced models like CosyVoice and SoVits, the system captures subtle details such as intonation, breathing patterns, and resonance to produce speech that sounds just like a real human voice.

"With our upgraded Text-to-Speech engine and advanced tools for music generation, voice cloning and synthesis, VoicePix 2.0 delivers unprecedented naturalness and emotional authenticity that can replicate human tone, pacing and expression.....As global demand for immersive, efficient and personalized content accelerates, we believe there is substantial opportunity to grow and create long-term value for our shareholders," said Aitan Zacharin, CEO of Core AI Holdings.