← All tutorials

Dictate Descriptions Instead of Typing

Say what the step does and let Whisper type it into the description for you.

Set Up the Transcriber

Voice input has its own provider and its own key, separate from the one the writing actions use. Both live in the same dialog: open the menu next to the ✨ button in a step description and choose AI API Settings, then scroll to AI Voice Input Settings.

Set Up the Transcriber. Folge, offline step-by-step guide software for Windows and Mac.
  • OpenAI Whisper: Your OpenAI key. Folge uses the Whisper model for the transcription.
  • Custom Whisper API Compatible: A Whisper server of your own, given an API Host and an API Path. The key is optional here, which it is not for the writing actions, so a local server needs no key at all.

Test Connection checks it before you rely on it. Settings save as you type.

Dictate a Description

  1. Select the step.
  2. Click the microphone button in the description toolbar.
  3. Press the record button and say what the step does.A waveform shows Folge is hearing you.
  4. Stop when you are done.The transcription is sent, and the text lands in the description.
Dictate a Description. Folge, offline step-by-step guide software for Windows and Mac.

Your operating system will ask for microphone permission the first time. On macOS that prompt appears once, and if you dismiss it you will need to allow Folge under Privacy and Security.

Teach It Your Vocabulary

Transcription hints is the setting that turns this from a novelty into something usable. Whisper is good at ordinary speech and bad at names it has never seen, so a list of the words you actually say fixes most of what it gets wrong.

Put your product names, systems, colleagues and acronyms in there, separated by commas: Northwind Ops, OAuth, Bergamo Foods, SKU, Kalmar. Without it, a product name comes back spelled the way it sounds.

Tip: Dictate, then rewriteSpeech comes out as speech: long sentences, false starts, "so then you". Dictate the content, then run Improve or Shorten over it to turn it into documentation.

What Leaves Your Computer

The audio you record, and nothing else. No screenshot is involved, so this is the one AI feature in Folge that never sends a picture of your screen.

It goes to the provider you configured, on your key and your account. If recordings of internal discussion cannot leave the building, point the custom provider at a Whisper server you run: see Set Up AI in Folge.

What this is good for

  • Talking through a process is faster than writing it, and closer to how you would explain it.
  • Describe forty steps without your hands leaving the mouse.
  • Get a first draft in a language you speak better than you type.

Make guides like this one

Folge captures a screenshot on every click, so a guide writes itself as you work.

System Requirements: Windows 7 ( partial support), 8, 8.1, 10, 11 (64-bit only). OSX > 10.10. Available in 🇬🇧, 🇫🇷, 🇩🇪, 🇪🇸 , 🇮🇹, 🇳🇱, 🇵🇹/🇧🇷 and 🇯🇵 languages.