Voice Craft AI: An AI-Powered System for Multilingual Dubbing and Lip-Syncing

Sajan Varghese, Sindhu Daneil

Abstract: Voice Craft AI is an AI-based voice synthesis and dubbing system that enables automatic translation and voiceover of video content into multiple languages while preserving the original speaker's voice. It uses a pipeline of tools including Whisper for transcription, Google Translate for translation, Edge-TTS for speech synthesis, and Wav2Lip for lip-syncing.

Keywords: AI Dubbing, Voice Synthesis, Multilingual localization, Whisper