V

VoiceStudio

Developed by debpalash

VoiceStudio, developed by debpalash, is a local-first desktop application for advanced audio generation and processing. It provides robust voice cloning, video dubbing, dictation, and long-form audio generation (e.g., audiobooks). Supporting 16 TTS and 11 ASR engines across 646 languages, its core workflow runs entirely locally without accounts or APIs, ensuring data privacy. It's compatible with macOS, Windows, and Linux, offering local REST/SSE/WebSocket and OpenAI-compatible audio APIs.

  • Local-first Voice Cloning and Design
  • AI-powered Video Dubbing with Translation
  • Integration of 16 TTS and 11 ASR Engines
  • Cross-platform Desktop Application with Open APIs
  • Embedded AI Watermarking and Detection
desktop