Voicebox
A local AI voice studio: clone voices, have text read aloud and dictate, no cloud required
Voicebox is a desktop app that lets you clone voices from short samples and generate speech in 23 languages. You can choose from eight TTS engines, including Qwen3-TTS, Chatterbox Multilingual and Kokoro. On top of that, you get hotkey dictation powered by Whisper. What sets it apart: you manage all the models from a single interface, and it runs on a wide range of GPUs (NVIDIA, AMD, Intel Arc, Apple Silicon) or, if needed, on the CPU alone.
How to try it
Commands from the official guides – just copy them.
Linux
# There's no ready-made package for Linux yet, so you have to build the app yourself.
# Requirements: Git, Rust, Bun, just (cargo install just) and the Tauri system packages
git clone https://github.com/jamiepine/voicebox.git
cd voicebox
# Set up dependencies
just setup
# Build the app; the output ends up in tauri/src-tauri/target/release/bundle/
just buildmacOS
# Download the DMG and install it as usual:
# Apple Silicon (M1–M4): https://voicebox.sh/download/mac-arm
# Intel Mac: https://voicebox.sh/download/mac-intelWindows (PowerShell)
# Download the MSI installer and double-click to run it:
# https://voicebox.sh/download/windows
# All versions: https://github.com/jamiepine/voicebox/releases/latestCommands from the official guide. New in the Toolbox since Nov 5, 2026.
Ask the AI assistant
Questions about Voicebox, installation or background? Our assistant knows this page and runs on our own machine, not in someone else's cloud.
The Assistant is an AI (Gemma 4) and can make mistakes – please check important details against the source. Questions are used only to generate an answer and are deleted after one hour. Please don't enter any personal data.
Comments
What do you think? Already tried it? Write it here, no sign-up needed.
Comments are public. Links aren't allowed, and we delete abusive posts. You can delete your own comment at any time in this browser. Learn more in the Privacy Policy.