I built SayKuku around two gestures that work together on your Mac:
Fn Voice Input. Dictate at the cursor in the text field you're already using.
Fn 2 Voice Agent. Tell it what you want done: generate a reply, work with text, answer a question, or take a supported action.
The second gesture is the part I'd love your feedback on. You don't need to select text or open a separate chat window to ask a question or draft something. Here are some examples of requests:
Fn dictates at the cursor. Double-tap Fn and ask Voice Agent to draft a reply, answer questions, summarize allowed window text, or follow up. Select text to rewrite or translate it; say 'make it shorter' to refine SayKuku's last output. Agent can also open links, start web searches, and run a named Apple Shortcut after confirmation. Free, open-source, native macOS 15+. Bring your own Qwen API key; cloud model usage is billed to your account.
