Skip to main content

​
When to use this mode

Use the Audio mode when your process knowledge lives in a recording rather than written notes — for example:
  • A verbal walkthrough you recorded while performing a task
  • A meeting or training session where a process was explained aloud
  • A voice memo describing steps in a workflow
Steppd transcribes the audio and structures the spoken content into sections and steps. You then answer a few clarifying questions before the document is created.

​
File requirements

DetailValue
Accepted formatsMP3, WAV, OGG, M4A
Maximum file size25 MB
Files larger than 25 MB cannot be uploaded. If your recording exceeds this limit, trim it or export it at a lower bitrate before uploading.

​
Steps

1

Go to the new document page

In the sidebar, click My documents, then click New document. Or click New document directly from the Dashboard.
2

Select the Audio card

On the mode-selection screen, click the Audio card.
3

Fill in optional metadata

Optionally enter a Title, Version, and Department. If you leave the title blank, the AI will infer one from your recording — you can edit it in the editor later.
4

Upload your audio file

Click the upload area and select your audio file. The accepted formats and size limit are shown beneath the upload area.
5

Click Generate draft

Click Generate draft. Steppd uploads your file, transcribes it, and analyzes the content. Transcription and analysis may take a minute or two depending on the length of the recording — the page shows a status message while it works.
6

Review the draft outline and answer questions

Once processing is complete, a draft outline appears with the proposed sections, along with clarifying questions. Answer as many as you can to improve the accuracy of the final document.
7

Create the document

Click Create document. The editor opens with the generated content, ready to review and edit.
All AI-generated titles, sections, and steps are fully editable in the editor after creation.