avatica

Avatica is a free, native desktop application — a creative studio for generating images, video, music, and speech using AI. Rather than subscribing to a cloud service, you bring your own API keys from providers you already use (Google Gemini, xAI, or OpenAI), and any generation costs go directly to your provider account. Everything else runs locally: your projects are plain folders on your disk and no content leaves your machine except the actual calls to whichever AI provider you select.

The workspace is organized into three modes. Create mode gives you a set of focused tools called apps — for example, text-to-image generation, video generation from a text prompt or an existing image, song generation from a prompt, and speech synthesis. There are also tools for building reusable building blocks: you can create a Character (with a portrait and description), a Scene, or an Object, then feed those into other tools. For instance, a Character combined with a Scene can produce a cinematic Shot, which a separate Cinema Studio app can animate into a video clip.

Compose mode provides a multi-track timeline where you drag your generated assets — images, audio clips, video segments — arrange them, trim them, layer text, and export an MP4. A Chat panel on the right side serves as an AI assistant that knows your project files and can chain tools together on your behalf.

Develop mode lets you build your own custom apps and asset types. The app is available as a downloadable installer and on the Mac App Store, and is licensed under GPL v3.