Everything CSuite can do.
Generate and edit text, images, audio, and video, plus multimodal chat and node-based workflows, in one desktop workspace. Run local models free on your hardware, or cloud models through Runware, OpenRouter and Replicate, or direct from vendors like OpenAI, Anthropic, Google and more, with your own API keys.
Text
Draft and edit documents in a full rich-text editor with inline AI: rewrite, translate, or retone a selection, generate images in place, and export to Markdown, HTML, or PDF. It works with any model, local or cloud.
Image
Generate images from a prompt, revise them with reference images, upscale or cut out a background in one click, and finish with built-in crop, resize, adjust, annotate, and compress tools.
Audio
Text-to-speech voiceovers, music, and sound effects in one panel, plus transcription of a recording or a video's soundtrack into text and subtitles. Audition a voice before you use it, clone one from a sample, or run speech fully offline on your own machine, then trim, fade, and level it in the built-in waveform editor.
Video
Generate single clips from a description, a photo, or start- and end-frames (in the cloud or locally on the GGML runtime), then extend, trim, crop, and re-time them, or build long videos on a multi-track timeline with AI drafting the whole cut for you.
Compositions
Put generated media together into a finished piece: a video on a multi-track timeline, or an audio piece with its own speakers and script, drafted by AI if you like.
Chat
Converse with any tool-capable model in the catalog, cloud or local, and generate media mid-conversation. Ask for a hero image and it lands in your project folder, not a chat log.
Workflows
Chain models and edits into node-based workflows: prompt in, generated and post-processed files out. Draw the graph yourself or describe it and let the built-in assistant wire it, then re-run whenever the inputs change.