Hermes Agent
— Open-source self-hosted AI agent with persistent memoryOpen-source self-hosted AI agent with persistent memory

Local voice cloning, dubbing, transcription, and text-to-speech

VoiceStudio is an open-source desktop app for local voice cloning, voice design, video dubbing, dictation, transcription, and audiobook creation. Its voice catalog covers 646 languages, with availability varying by engine.
It runs on macOS, Linux, and Windows through WSL. The app can clone a voice from a short clip, generate voices from descriptions, transcribe audio or video, translate and re-voice video while preserving speakers and timing, and create multi-voice or chaptered audiobooks from scripts and EPUB files.
VoiceStudio is available for local use without sending voice data to an external server. The site describes it as free for personal use and provides a shell-based installer and an open-source GitHub repository.
Highlights
Used it? Write the first review.
Open-source self-hosted AI agent with persistent memory
Open-source local design workspace powered by coding agents
Real-time global intelligence dashboard with live maps and AI alerts
Compresses CLI output to reduce AI coding agent token usage
Private on-device AI assistant for documents and workflows
An agent development environment for parallel coding workflows