Voicebox
Open-source local-first AI studio for voice cloning and dictation
Screenshots
A closer look at the product interface and key surfaces.
Screenshot viewer
At a glance
- Primary use case
- Open-source local-first AI studio for voice cloning and dictation
- Best for
- Voice — Voice, Whisper
- Stack
- docker, javascript, nodejs, python
- License
- MIT
- Maintenance
- 4 weeks ago
- Access
- Open source · Self-hosted
- Documentation path
- https://docs.voicebox.sh/
About this tool
Voicebox is a local-first AI voice studio and open-source alternative to ElevenLabs. It enables users to clone voices, generate speech in 23 languages, and dictate text globally using local models for complete privacy and control.
Repository
59,380
7,444
529
MIT
Features
- Allows users to clone any voice from just a few seconds of audio.
- Supports speech generation in 23 languages across 7 different engines.
- Enables global dictation into any application with a dedicated hotkey.
Related tools
VoiceInk
Voice
Privacy focused offline voice to text and transcription for macOS
Speakr
Voice
Self-hosted AI transcription and intelligent note-taking platform
Freestyle
Voice
Fast local first voice to text dictation for your desktop
Openclaw
AI Automation
Your own personal AI assistant for every platform and device
ECC
Developer Tools
Harness native operator system for AI agents and agentic optimization
Hermes Agen
AI Automation
Self-improving AI agent with autonomous learning and skill creation
Published 1 day ago