One orb. Five personalities.
Scroll to meet them — each rewrites what you say differently.
Every word, exactly as spoken — no rewrite, no delay.
Cleans up grammar and filler, keeps your own words.
Turns a ramble into crisp notes and a dash list.
Rewrites into a polished message, ready to send.
Reforges a spoken idea into a structured AI prompt.
Prompt Claude out loud.
The fastest way to write a prompt is to say it. Outspoken floats over Claude Code, and your words are ready to paste into the composer — punctuated, translated if you want, ready to send.
Welcome to Claude CodeReady to paste, wherever you're working.
Refactor this without breaking the tests
Your thoughts move faster than your fingers.
Average typing ~40 WPM vs. speaking ~150 WPM.
English WER on the Hugging Face Open ASR Leaderboard, shown as accuracy. Apple's built-in engine is OS-managed and isn't on that leaderboard.
Every engine, running on your silicon.
Rewriting runs on Apple Intelligence or any of five downloadable MLX models. Three separate engines — Apple, Parakeet and Whisper — handle transcription. Swap either anytime.
On-device, no download — the default backend.
1.7B, 4B or 8B — fully on-device via MLX.
3B open weights, running locally through MLX.
1B lightweight open weights, running locally through MLX.
No download · live captions · wide locale support.
~1 GB · 25 languages · near-instant transcription.
~1.6 GB · 99 languages · the most accurate engine.
The whole journey fits in your Mac.
No account. Your voice and your words never leave your Mac. The models run on the Neural Engine, so it works the same in airplane mode.
On your Mac. In your pocket.
On the Mac, each transcript lands on your clipboard, ready for ⌘V. The iPhone keyboard goes one better — hold the orb, speak, and the words land straight at your cursor.