VOICE STUDIO / DOCS

Installation & Getting Started

Install VoiceStudio, choose a compatible model, generate your first audio and export it. Review RAM, storage and optional GPU requirements.

Install the desktop app

Choose the installer for your system on the download page. macOS offers separate Apple Silicon and Intel builds; Windows and Linux builds are x64. Follow the installer’s instructions.

Download free

Download a compatible model

Open the model catalogue in the app. Choose an engine that supports your hardware, task, and target language. Review its license and storage requirements, then download it with an internet connection.

Create your first audio

Open the text-to-speech studio. Select your installed model and a voice, enter a short script, and generate. For voice cloning, add a clean reference recording that you have permission to use.

Export and keep creating

Listen to the result, adjust your script and settings, and export the audio. Keep your reference recordings and project files organized for future sessions.

Before you start

Windows 10 / 11, macOS, or Linux
Around 8 GB RAM to get started; requirements vary by model
Free disk space for the app and model downloads
Internet connection for the initial model download
A supported GPU is optional and can improve speed

Need a hand?

If a model fails to load, check its hardware and memory requirements and read the app’s logs. For software issues, search existing GitHub issues or report a reproducible problem upstream.

Visit GitHub issues

Your next story starts here.

Find your voice. Make it heard.

Download freeFree to download. Yours to explore.