VoiceStudio

Overview

VoiceStudio brings voice generation and speech workflows to your own hardware without requiring cloud processing. Clone or design voices dub videos create audiobooks transcribe recordings and dictate text using local models with optional API and MCP integrations for AI agents. It supports 646 languages and runs on Windows macOS and Linux.

Key features

• Voice cloning
• Voice design
• Text to speech
• Speech to text
• Video dubbing
• Audiobook creation
• Dictation
• Transcription
• 646 language support
• Local AI models
• Local API
• MCP integration
• Batch processing
• Watch folders
• GPU acceleration
• Open-source AGPL-3.0 license