Skip to main content

Use cases

Voice Type for developers

Hold a hotkey, talk through the change, release to insert a clean explanation. Perfect for commits, PRs, and tickets.

Your code base knows shadcn, tRPC, Prisma, Redis, and Vercel. Dictation should too. Test with your own phrases—if you edit less, you ship more.

Spoken text (ground truth)
Shipped a Next.js app with shadcn ui and tRPC. Deployed on Vercel. Added memcached and Redis. Switched to TypeScript strict.

Example outputs. Use the copy blocks below to try your own phrases.

Apple Dictation (example)
Shipped a Next JS app with shade CN UI and TRPC. Deployed on Versell. Added mem cash and Redis. Switched to Type Script strict.
Voice Type (raw)
Shipped a Next.js app with shadcn ui and tRPC. Deployed on Vercel. Added memcached and Redis. Switched to TypeScript strict.
These are example outputs. Use your own phrases in the copy blocks below to compare raw transcripts.

Where it fits

  • Explaining a change at the top of a file.
  • Writing a clear commit message without losing flow.
  • Filing a ticket with real steps and context.

Setup in one minute

  1. Install Voice Type from the Mac App Store.
  2. Pick a hotkey that does not collide with your editor.
  3. Tap the hotkey, talk, and tap again to stop.

Works in VS Code, Xcode, Cursor, JetBrains IDEs, and your browser. The app types wherever the cursor lives.

Try a real phrase

Copy one of these and read it out

  • Shipped a Next.js app with shadcn ui, tRPC, and Zustand. Deployed on Vercel. Used pnpm and Homebrew. Added memcached as a sidecar.

  • Upgrade plan: migrate to Postgres with Prisma, add Redis for queues, keep Nginx in front of Node. Switch to TypeScript strict.

  • Set up GitHub Actions, run Vitest, then publish to npm. Add a changelog and semantic release.

Tip: copy a line, place your cursor in a text field, and read it out. Then try the same line with Apple Dictation. Compare the raw text before any rewrite.

Dictate the same line with the built-in tool and with Voice Type. Watch library names, service names, and edit time. Use your own snippet if you prefer—product names are a great test.

Why technical terms stick

Clean input
Trim low rumble. Normalise loudness. Cut silence. Feed the recogniser a clear signal. Result: product names and short codes survive the trip.
Noisy input
Room noise and uneven levels blur word boundaries. Result: names and acronyms fall apart, edits pile up.

Voice Type conditions the input before recognition, so technical nouns stay accurate.

Privacy and speed

Audio stays on your Mac. The last chunk finalises quickly, even on older M1 machines, so long PR descriptions and tickets still feel responsive.

Start the free 7-day trial