use case · claude
Talk to Claude. Show it what you see.
The better the context, the better Claude's answer — and nobody wants to type three paragraphs of context. Say it instead, and when it's about something on your screen, send the annotated thing itself.
voice for every claude
Wherever Claude takes text, dictation works: put the cursor in the message box, press Ctrl ` , talk, and your words appear as editable text — read it over, trim it, send it. Long, thoughtful prompts stop being a typing chore; a spoken minute is roughly three typed ones.
Thinking out loud rarely comes out tidy. The Prompt voice mode reshapes a spoken ramble into a clear request before it lands — it runs free on the built-in local model or your own Ollama server, and Pro can route it through your own Claude or OpenAI account.
give claude your eyes
A design draft that needs feedback, a spreadsheet cell that makes no sense, a paragraph in a contract, a diff in a code review. Press Alt ` , drag over the region, draw a box around the part in question while you ask about it — and paste. Claude receives the annotated screenshot and your transcribed words together, in one go.
In the terminal with Claude Code, delivery adapts: it gets your words plus the screenshot's file location — which is what a terminal can use. Chats, docs and editors get the image itself. How delivery adapts per app →
private by default
Speech becomes text on your device — your audio is never uploaded, and the app tracks nothing about you. Claude sees exactly what you paste, and only that. The full network-use table →
Windows 10/11 today — macOS and Linux builds are on the way. Also see dictating to ChatGPT and speech to text for Windows.