We’re always working to enhance your experience! Keep up with CSuite’s latest updates and new features. The app updates itself automatically, or you can get the latest version from the download page.
Audio gained a working format converter, edits that keep the source format, an info popover with prompt reuse, prompt history, and a cost hint. Fish Audio S2.1 Pro can now clone a voice from a reference clip you pick in the app.
ModelFish Audio S2.1 Pro
Models splits into your connected providers and a Defaults tab where you set the model each workspace starts with. Those picks are shared with the model button everywhere else.
Text to speech voices have a sample you can play from the picker.
The HuggingFace runtime failed to install on Windows and Ollama setup could hang on Ubuntu. Both now complete.
Documents gained a slash menu for inserting blocks, search within a document, an outline for jumping between headings, live word and character counts, templates to start from, export, and media you can embed inline. Files can be attached to a document as context for the AI, and the inline suggestions that write ahead of you got better.
Every generation workspace now opens on the lowest cost quality, resolution, and duration a model offers, so nothing expensive runs because you did not change a default.
Runware video models were missing the start and end frame and settings inputs their Replicate counterparts had, and Runware image models were missing reference and starting images.
Actions that used to fail quietly now raise a toast explaining what went wrong.
The selection ribbon in the text editor only worked with local models and did nothing on a cloud provider.
Dropping images, audio, or video onto a modality sidebar imports them into your project folder, and dropping media into a text document embeds it inline.
Setup is six steps that end with your license: what CSuite is, connecting providers, what each workspace does, chat and workflows, and choosing a folder.
MiniMax Speech 2.8, Fish Audio S2.1 Pro, ACE-Step v1.5, Kimi K3, and Claude Sonnet 5 were added. A local model entry that pointed at a tag which did not exist was corrected, and Nano Banana 2 Lite was fixed to stop invoking the full model at roughly twice the cost.
ModelsSpeech 2.8Fish Audio S2.1 ProACE-Step v1.5Claude Sonnet 5Nano Banana 2 Lite
Cancelling a text generation threw an error instead of stopping cleanly.
CSuite now checks for new versions in the background, downloads them quietly, and installs on your next quit. Account has an Updates panel with the current status, a manual check, and a switch to turn automatic updates off.
The window could render with no background at all on Linux setups without compositing.
The first public release of the desktop app: text, images, audio, video, chat, and workflows in one place, running local models on your own machine or cloud models through your own provider keys. It ships for macOS on both Apple silicon and Intel, for Windows, and for Linux as an AppImage.
No subscriptions. No seats. No renewals. Buy CSuite once, future updates included.
Secure checkout via Stripe. Already have a license? Download the app