Skip to content
CSuite
Guide

How to use CSuite.

A friendly, end-to-end guide to the app: from installing it the first time, to generating your first image, to chaining models into a multi-step workflow. No prior AI experience needed.

Part 1

Get started

1.1

Install & setup

CSuite is a native desktop app for macOS, Windows and Linux. It runs entirely on your computer. There is no website to log into, no account to create, and nothing to install in your browser.

1
Download the app
Head to the download page and grab the build for your operating system. On macOS you’ll get a .dmg; on Windows an .exe installer; on Linux an AppImage.
2
Install and open it
Run the installer and launch CSuite from your apps. The first time you open it, the app walks you through a short setup wizard: a quick tour of what it can do, then a single setup screen.
3
Set up your models
On the setup screen, tick the local runtimes you want (Ollama and the Hugging Face runtime are both on by default) and paste API keys for the cloud platforms you use (Replicate, Runware). The wizard also fetches ffmpeg, the engine behind local audio and video editing. Everything here is optional; you can finish later from the Models screen.
4
Activate your license (optional)
The last step asks for your license key if you’ve purchased CSuite. You can skip it and activate later from the Account screen. The app will keep working in the meantime.
TipYou can add more providers or pull more local models any time from the Models screen. The first-run wizard is just a friendlier on-ramp for the same controls.
1.2

The app layout

CSuite has a single window with three main areas:

  • The menu: the strip of icons down the left side. The CSuite mark at the top opens the Dashboard (recent files and quick actions); below it sit the four modalities (text, image, audio, video), then Chat and Workflows, and finally Models and Account. Hover an icon to see its label.
  • The sidebar: the list of files in your current modality. For example, in the Image workspace it shows every image in your project folder with a small thumbnail and filename.
  • The main panel: where you preview, edit and generate content. A model picker sits above the preview and a prompt sits below it, so you can iterate without leaving the workspace.

Each workspace is built around the same idea: pick a model on the right, type a prompt, and the result lands in your project folder and shows up in the sidebar.

1.3

Your project folder

The project folder is the heart of CSuite. Everything you generate or edit is saved there as a real file you can open in Finder, File Explorer, or any other app.

  • The app starts with a sensible default folder, so there’s nothing to configure up front. A folder pill above the sidebar shows which folder you’re in; click it to switch.
  • Each workspace shows the files it can open: the Image workspace lists the images in the folder, the Audio workspace the audio files, and so on.
  • You can drop existing files into the folder from outside the app; click the refresh button next to the folder pill to pick them up.
  • Switching to a different folder gives you a clean workspace, great for keeping client projects separate.
  • Use the menu on any file in the sidebar to reveal it in your operating system’s file manager, duplicate it, or delete it.
  • Select a file and press Delete or Backspace to remove it. The app shows a confirm dialog first so you can’t lose work by accident.
TipBecause everything is just files on disk, you can back your project up with the same tools you already use (Time Machine, Dropbox, iCloud, a USB drive) without any export step.
Part 2

Models

2.1

AI model providers

An AI model is the engine that does the actual generating. CSuite lets you choose from two kinds of providers:

Cloud providers

CSuite connects to two cloud platforms (Replicate and Runware) that run powerful models on their own servers. Through them you reach models from OpenAI, Google, Black Forest Labs, ByteDance, Meta and more, with a single key per platform. CSuite talks to them directly using your own API key. Your prompts never pass through us.

1
Create an account with the provider
Visit the provider’s website and sign up. Most cloud providers charge per-use, so you’ll need to add a payment method to their account, not to CSuite.
2
Generate an API key
Find the “API keys” section in their dashboard and create a new key. Copy it.
3
Add the key to CSuite
In CSuite, click Models in the menu, pick the provider from the list, paste the key into the API Key field and click Save key. The app validates the key right away. A green “Key is valid” message means you’re ready.
TipYou can reveal a stored key, replace it with a new one, or remove it from the same provider screen at any time.

Local providers

Local providers run open-weight models directly on your computer. Once a model is downloaded you can use it offline, with no per-request cost, and nothing leaves your machine. CSuite supports two runtimes:

  • Ollama: the easiest way to run text models like Gemma, Llama, Mistral and Qwen. CSuite can either bundle Ollama for you or use an existing Ollama install you already have.
  • Hugging Face runtime: runs ONNX-exported open models. CSuite installs the runtime for you on first use.

How well a local model performs depends on your computer’s memory and (on Macs) your Apple silicon chip. For Ollama models, CSuite compares each model’s needs against your machine and blocks the download if it needs more RAM than you have.

2.2

The Models screen

Click the Models icon in the menu to see every model available to you, grouped by provider. From here you can:

  • Browse the catalog of local models that you can download. Each row shows the model size, what it’s good at, and whether your computer can run it.
  • Download a local model: click Download and watch the progress bar. You can keep using the rest of the app while it downloads.
  • See which models are already installed and how much disk space they’re using.
  • Hide models you don’t want cluttering up the picker when you’re generating content.
  • Delete models you no longer need to free up disk space.
Part 3

Create

3.1

Working with text

launch-notes.md
Claude · Sonnet 4.6

We’re launching a new espresso grinder built for the curious home barista: precision burrs, single-dose hopper, and zero retention. Available next month.

RewriteContinueShorterLongerToneFix
Make it punchier and add a call to action…

The text workspace is a rich-text editor for drafting, rewriting and brainstorming with AI assistance. It opens plain text, Markdown and HTML files.

Generating text

1
Pick a model
On the right, choose a provider and a text model. Faster local models are great for drafts; cloud models are great for polish and reasoning.
2
Type a prompt
In the prompt box at the bottom, describe what you want, e.g. “Write a 3-paragraph product launch announcement for a new espresso grinder.” Press Send.
3
Watch it stream
The reply appears in the editor, word by word. You can stop generation at any time. The result is saved automatically into your project folder.

Inline editing tools

Select any piece of text and a small toolbar appears with quick AI actions:

  • Shorten: tighten the selection.
  • Expand: flesh the selection out with more detail.
  • Improve: rewrite the selection for better clarity.
  • Generate image: in Markdown and HTML documents, turn the selected text into an image that’s inserted right after it.
TipCapable models also support a Reasoning depth setting. Turn it up for harder questions and the model will think for longer before replying.

Inline images and ghost suggestions

You can ask the model to generate an image right inside a document. It appears inline and is saved alongside the text. When you pause typing for a few seconds, the editor can also suggest a few words ahead in faint grey; press Tab to accept, Esc to dismiss, or use the small Accept / Try again / Cancel controls that appear by the caret.

3.2

Working with images

coastline-dawn.png
ReplicateFlux 1.1 Pro16:9PNG+ reference
cinematic coastline at golden hour, soft morning mist…Generate

The image workspace is built around a thumbnail grid sidebar and a large preview panel.

Generating an image

1
Pick a model
Choose a provider (Replicate or Runware) and an image model (e.g. Flux 2, Nano Banana 2, Seedream, GPT Image 2).
2
Describe the image
In the prompt box, write what you want to see. Be specific: subject, style, lighting, mood.
3
Pick aspect ratio and format
Choose an aspect ratio (square, 16:9, 9:16, 4:3, 21:9 and more; the exact choices depend on the model) and an output format (PNG, JPG, WebP).
4
Add reference images (optional)
Some models accept reference images: upload one or more images the model should take inspiration from. If a model supports it, you’ll see an upload row. The maximum number of references depends on the model.
5
Generate
Click Generate. The new image is saved to your project folder and selected automatically.

Editing images

A toolbar above the preview holds the editing tools. Each edit overwrites the file in place, or, with Save a new copy ticked, keeps the original and writes a new file alongside it.

  • Resize: pick a preset size (240p up to 1080p) or set a custom width and height with an optional aspect-ratio lock. CSuite uses high-quality resampling under the hood.
  • Crop: drag a rectangle in the preview, freely or to a fixed aspect ratio.
  • Rotate: rotate the image in 90° steps.
  • Annotate: draw directly on the image.
  • Quality: adjust JPEG compression (for JPEG files).
  • Format: convert between PNG, JPEG and WebP.

To re-generate from an existing image, add it as a reference image when you generate (above), or use Chat or a Workflow.

3.3

Working with audio

voiceover.mp3
ElevenLabs · Rachel
0:00trim · 0:14 → 1:101:30

The audio workspace handles voice, music and sound effects. It opens MP3, WAV, FLAC, OGG and AAC files.

What you can generate

  • Voice (text-to-speech): type a script, pick a voice model, and get back natural-sounding speech.
  • Music: describe a track and let a music model compose it.
  • Sound effects: describe a sound (“a rusty door creaking open”) and get a short clip.

Editing audio

  • Trim: cut the clip down to a specific start and end time.
  • Fade: add a fade-in and/or fade-out.
  • Volume: turn the clip’s gain up or down.
  • Speed: speed the clip up or slow it down.
  • Convert: export the clip to WAV.

The built-in player has play, pause and a scrub bar so you can preview before saving.

3.4

Working with video

opening-shot.mp4
Veo 3.1 Fast
start frame
··· generated motion ···
end frame
0s
6s

The video workspace handles MP4, WebM, MOV and AVI files. For stitching multiple clips, audio tracks and titles into a single longer video, see Custom video.

Generating video

1
Pick a model
Choose a video model, for example Veo 3.1 Fast or Seedance 2. Different models have different strengths and speeds.
2
Describe the scene
Write a clear, visual prompt. Mention motion, camera, lighting and mood, not just the subject.
3
Add a start or end frame (optional)
Some models let you upload an image to use as the first frame, the last frame, or both, handy when you want the video to continue from a hero image you’ve already generated.
4
Generate and wait
Video generation can take a couple of minutes. The progress bar shows what stage the job is in. You can keep using the rest of the app, or cancel the job at any time.

Editing video

  • Crop: crop the frame freely or to a fixed aspect ratio (1:1, 4:3, 16:9, 9:16 and more).
  • Resize: choose a fixed height (240, 360, 480, 720, or 1080) and the width is calculated automatically.
  • Transcode: convert the container between MP4, WebM and MOV.
TipAll video edits run locally using a bundled copy of ffmpeg. They never leave your machine, even if you generated the video with a cloud model.
3.5

Custom video

espresso-launch16:9chattimelineDownload…
Helio launch
0:03 / 0:09
0s2s4s6s8s
Title
Helio launch
Pre-order
Image
Hero
Generating…
Video
Demo clip
Audio
Voice + music bed

Custom video is a separate creation mode for stitching multiple clips, images, audio tracks and titles into a single longer video. Where the regular video workspace produces one short clip at a time, custom video gives you a multi-track timeline and renders the whole composition out to a single MP4 (or WebM, or MOV).

Starting a composition

1
Open the video workspace
From the side menu, open Video.
2
Create a composition
The video sidebar has two tabs: Clips (single video files) and Compositions. Switch to Compositions and click the + button. A new composition opens in the editor with a starter title clip; the first time, the app also asks you to pick the models it should use.
3
Pick an aspect ratio
Use the aspect-ratio pill in the toolbar to pick 16:9, 9:16, 1:1, 4:3 or 21:9. You can change this later. If you’ve already edited the timeline, the app will offer to reposition and rescale every clip with AI so the composition still looks balanced.

Drafting with AI

The fastest way to start is to describe what you want. CSuite drafts a script, scenes and titles for you, then generates the images, voice-over, music and SFX in parallel.

1
Open the AI prompt sidebar
Click the chat icon in the editor toolbar to reveal the AI prompt sidebar on the right. (It’s open by default.)
2
Pick your models
Click Models in the editor toolbar and choose which text model does the writing — local (Ollama, Hugging Face) or cloud (Replicate, Runware) — plus the image, voice, music and sound-effect models the draft should use.
3
Describe the video
Type a one-line idea: “a 15-second product teaser for a new espresso grinder, warm cinematic vibe, with a voice-over hook and a closing CTA card.” Press Enter (or ⌘⏎ / Ctrl+Enter) to send it.
4
Watch the timeline fill in
The script, scene timings and title cards render immediately so you can play back what you have. Images, voice-over, music and sound effects then resolve in parallel. Each clip shows a shimmer placeholder until its asset arrives. If any individual asset fails, the rest still land and you get a single Retry failed layers button at the end.

Editing the timeline

  • Move and resize: drag a clip’s body to move it, drag its right edge to resize. Clips snap to whole-second ticks and to the start and end of every other clip.
  • Inspector panel: click any clip to edit its properties: start, duration, fade in/out, plus per-kind controls (font and text for titles, fit for images, muted for video, volume for audio).
  • Add clips: use the + Text / Image / Video / Audio palette to insert a new clip. The image, video and audio buttons open a picker listing files from your project folder.
  • Delete: select a clip and press backspace.
  • AI follow-up edits: go back to the AI prompt sidebar and ask for a change (“make the music quieter, add a logo at 3 seconds”) and CSuite produces a full timeline replacement that preserves your other clips.

Visual coherence

When the AI bootstraps a composition, it also picks a short visual theme (palette, lighting, mood) that gets appended to every image-generation prompt. The result is a sequence that feels like one shoot rather than a collage of unrelated frames. You don’t need to manage this yourself; it lives in the composition file and travels with the project.

Rendering to a file

When the timeline looks right, click Download to open the export settings.

  • Resolution: Native, 480p, 720p, 1080p or 2160p. Aspect ratio is preserved.
  • Framerate: Native, 24, 30 or 60 fps.
  • Format: MP4 (H.264), WebM (VP9), or MOV (H.264).

The rendered file lands in your project folder as a regular video file alongside any single-clip generations, ready to play, edit further or share.

TipIf a voice-over comes back longer than the AI estimated, CSuite auto-extends the audio clip and ripple-shifts subsequent clips so nothing gets cut off mid-sentence.
Part 4

Operate

4.1

Chat

Promo thread
Llama 3.1 · local
Make a hero image of a misty mountain at dawn, 16:9
Saved · misty-mountain.png
Now narrate the scene in a calm voice
ImageAudioVideoask in plain language, chat picks the tool

Chat is a single conversational workspace where you can talk to a model and produce media in the same thread. Click the chat icon in the menu to open it.

Setting up a chat

1
Pick your chat model
Open the chat’s model panel and choose a tool-calling text model. Chat works by letting the model call tools to generate and edit media, so it needs a model that supports tool calls: a local Ollama model or a cloud model on Runware. When you create your very first conversation, the app pops the model picker open automatically so you don’t hit a “no model selected” error on your first send.
2
(Optional) pick image, audio and video models
The chat can also generate other media for you. Pick which models it should reach for when you ask it to make an image or a video — and for audio, separate slots for speech, music and sound effects.

What the chat can do

  • Stream replies from the chat model.
  • Generate a new image, sound or video on request: “make me a hero image of a coastline at sunset”.
  • Edit the most recent media inline: “crop this to 16:9”, “trim the first two seconds”, “convert to WebM”.
  • Take a previous image as a starting point and produce a variant from it.
  • Use earlier images as the start and end frames of a new video.
TipThere are no special commands to learn. Just ask in plain language (“turn that into a square”, “make a 30-second voice-over”) and the chat picks the right tool itself. With a vision-capable local model you can also attach an image to a message and ask questions about it.
4.2

Workflows

A workflow is a visual diagram that chains models and edits together. Think of it as a recipe you can run again and again, great for repeatable jobs like “turn a blog post into a voiced video with subtitles”.

The node types

  • Input: your starting point. A typed prompt, an image, an audio clip or a video.
  • Model: runs an AI model. Connect inputs to the “prompt”, “instructions” or media handles, and the node generates an output.
  • Edit: a deterministic transformation: resize, crop, trim, convert, transcode.
  • Combine: merges several files into one. Use it to play tracks together, or to glue clips end-to-end.
  • File: saves the final result into your project folder.
  • Note: a free-form sticky-note for labelling sections of the canvas. Notes have no inputs or outputs and never block a run.

Building a workflow

1
Create a new workflow
Click the workflow icon in the menu, then the + button. You can create a blank workflow, start from a template, or import a workflow file someone shared with you.
2
Add nodes to the canvas
Open the Add Node menu in the toolbar, or use the single-key shortcuts: I input, M model, E edit, C combine, F file, N note.
3
Connect them
Drag from one node’s output dot to another node’s input dot. Different colours show what kind of content can flow between them.
4
Configure each node
Every node’s settings sit right on the node. For Model nodes, pick the provider and model. For Edit nodes, choose the operation.
5
Run it
Click Run to execute the whole graph, or use the Run button on an individual node to re-run just that section of the graph. Independent branches run in parallel. You can Stop at any time.
TipWorkflows can be exported as JSON files and shared with teammates. Anyone who imports the file gets the same graph (they still need their own provider keys to actually run it).
Part 5

Manage

5.1

Account & license

The Account screen has five sections: Analytics, License, Updates, Feedback and Reset. Provider keys are managed under Models, not here.

Analytics

  • See total spend, request count, and token usage across the last 7, 30, 90 days, or all time.
  • Break it down by provider, model, and modality so you can spot which workflow is eating your budget.
  • Local-provider rows show $0.00. They’re free to run, and they’re tracked alongside cloud usage so you can compare apples to apples.

License

  • Activate a license: paste your key and click activate. The app validates the key online once, then stores a signed receipt that works offline.
  • See your license status: active, in its offline grace window, expired, or moved to another machine, along with when it was last validated. The app re-checks periodically in the background.
  • Deactivate a machine: frees up the seat so you can use the license on a different computer.
TipLost your license key? Email us at support@csuite.so with the email you used to purchase and we’ll resend it.

Updates

  • CSuite keeps itself up to date: it checks for new versions in the background, downloads them quietly, and installs on the next restart. When an update is ready, a Restart to update button appears here, and a small indicator shows in the side menu while one downloads.
  • Prefer to stay in control? Untick Automatically download and install updates and use Check for updates whenever it suits you.
  • If updating fails repeatedly, the app points you to the website to download the latest version manually.

Feedback

Send bug reports and feature requests straight from the app and track their status over time. Each one can come back with comments as we follow up. Sending feedback requires an activated license.

Reset

Reset returns the app to a fresh state: it clears your local app configuration and relaunches so you can set it up again. Your generated content stays put; anything in your project folder is left untouched.

Part 6

Trust & help

6.1

Privacy & data

Where each thing goesLocal-first
Files
your folder
your folder
stays local
Prompts
CSuite
provider you picked
direct, your key
API keys
your machine
your machine
stays local
We never seeyour prompts, generations, files, keys, or which models you use.

CSuite is local-first. Here’s exactly where your data goes:

  • Your files live in the project folder you picked. They are never uploaded anywhere by CSuite.
  • Your prompts go directly to whichever provider you picked for that generation. Local providers stay on your machine; cloud providers receive the prompt through your own API key.
  • Your provider keys are stored locally on your computer, encrypted at rest with your operating system’s secure storage (Keychain on macOS, DPAPI on Windows, libsecret on Linux), never on our servers.
  • Your license is verified online when you first activate it; after that the app uses a signed receipt that works offline.
  • What the app tells our servers: license checks and feedback send only what’s needed to do the job (your license key, app version, platform and a machine identifier), and update checks just fetch the release feed. Nothing else.
  • What we never see: your prompts, your generations, your project files, your API keys, or which models you use.
6.2

Troubleshooting

A generation failed

  • Check the model picker. Is the right provider selected?
  • Open Models, click the provider, and press Save key again to re-validate. Expired or invalid keys are the most common cause.
  • Some cloud providers throttle accounts that run out of credit. Check your usage and balance on the provider’s dashboard.

A local model is stuck or slow

  • Bigger models need more memory. If your machine has limited RAM, try a smaller model from the catalog.
  • Restart the app. Local runtimes free up memory on quit.
  • In the Models screen, try deleting and re-pulling the model if a download was interrupted.

A video edit was canceled or didn’t finish

  • Quitting the app while a video edit is running cancels the job. Re-run it once the app is back open.
  • Very large source files take time. The progress bar shows how far along the edit is.

Still stuck? See Support below for how to get in touch.

6.3

Support

CSuite is built and supported by a small team. Every email goes to a real person, and we read every one.

  • Email support@csuite.so for bugs, questions, license help, and feature requests.
  • Include your operating system, a short description of what you were doing, and (if relevant) the provider and model you had selected. The more we know up front, the faster we can help.
  • Lost your license key? Email us from the address you used to purchase and we’ll resend it.
  • Have an idea? We genuinely want to hear it. The same inbox is the right place.
TipBecause everything in CSuite is files on disk, you can almost always attach the relevant file (or a screenshot) to your email without worrying about exporting first.
6.4

Refund policy

CSuite is a one-time purchase, sold with a no-questions-asked refund window. We’d rather you spend money on something you love than feel stuck with something you don’t.

  • 7-day refund: if CSuite isn’t the right fit for any reason, email us within 7 days of purchase and we’ll refund your order in full.
  • No forms, no surveys: a one-line message is enough. We don’t require a reason, though we’re always grateful when people share one so we can improve the app.
  • How it works: refunds are issued to the original payment method via Stripe (typically 5 to 10 business days to land back on your statement). Your license key is deactivated as part of the refund.

To request a refund, email support@csuite.so with the email address you used at checkout.

Launch offer · 50% off

One-time payment. Yours forever.

No subscriptions. No seats. No renewals. Buy CSuite once, future updates included.

$98$49
Pricing

Secure checkout via Stripe. Already have a license? Download the app