Free public beta
Download CueTwin Beta
For Windows 10 and 11 (64-bit). Free during the public beta. Paid licences come later through Lemon Squeezy.
Windows 10/11 64-bit · v1.2.0 · AI models (roughly 8 GB) download on first launch. View releases on GitHub
Free during the beta
CueTwin is free for the whole public beta. There’s no trial timer.
Paid licences later
Paid licences come later through Lemon Squeezy. Pricing hasn’t been decided, and nothing is for sale yet.
Bugs go to GitHub
Report problems on GitHub Issues. It’s a beta, so expect rough edges.
A small installer, then a one-time model download
The installer itself is kept small enough for GitHub Releases. The AI models are not in it: they are a separate download that CueTwin fetches on first launch (roughly 8 GB), so you need an internet connection and at least ~8 GB of free disk space for that. After that, the built-in assistant runs locally, with no API key. Voice cloning models are downloaded separately during voice setup. Exact sizes will be confirmed with the first published build.
System requirements
| Component | Recommended (beta target) |
|---|---|
| Operating system | Windows 10 or 11, 64-bit |
| Memory | 16 GB RAM |
| Graphics | A compatible GPU is recommended. CPU-only operation is supported, but slower; real-time speed is not promised. |
| First run | An internet connection. On first launch CueTwin downloads its local AI models (roughly 8 GB); after that the built-in assistant runs locally. |
| Voice cloning | Python 3.11 (64-bit) from python.org, plus an internet connection to install the voice runtime and download the speech models |
| Disk space | At least ~8 GB free for the AI models, plus space for your projects (and the voice models, if you set up voice cloning). Exact figure confirmed with the first build. |
These are the beta’s target specs, not measured minimums. Professional voice training can need more memory and compute than generating speech.
Install and set up
- Download the beta for Windows (64-bit) using the button above, once it’s live.
- Run the installer (
CueTwin-Beta-Setup-x64.exe) and launch CueTwin, choose a writable folder for its data, and complete first-run setup. - Let the AI models download. On first launch CueTwin downloads its local AI models (roughly 8 GB). Stay online and keep at least ~8 GB free until it finishes; after that the assistant runs locally.
- Pick a projects folder. New projects default to
Videos\CueTwin; change it from File › Choose Projects Folder so recordings land on a drive with room. - For voice cloning, install Python 3.11 (64-bit) from python.org and tick “Add to PATH”.
- Install the voice runtime from inside CueTwin. It needs an internet connection: it installs its Python dependencies (a large download, with NVIDIA GPU or CPU builds chosen for your PC) and fetches the Qwen speech and Whisper models. Voice Design uses one more model download.
- Make your first voice in Voice Studio with an instant clone from your own recording, then generate narration and listen to it before using it.
Report a bug
Open an issue on GitHub. A good report includes:
- App version
- Windows version, CPU, GPU and RAM
- Numbered steps to reproduce the problem
- What you expected to happen, and what actually happened
- The exact error text, if any
- Whether a restart or retry helped
- Optional: scrubbed logs, or a sample you are authorised to share
Please don’t post licence keys, API keys, or private recordings and footage in a public issue.
Only attach media you choose to share, and only voice samples you’re authorised to share.
Reports sent from the app become public GitHub issues. See the privacy page for what a report contains and where it’s stored.