How to make a tutorial video with AI

Make a clear tutorial video by recording your screen and camera once, then letting an AI agent cut mistakes, add step titles, zooms, captions and chapters. A practical workflow for software tutorials.

Try it free

Short answer: Plan the steps, record your screen and camera in one take (pause and repeat a sentence when you slip), then edit: cut mistakes and pauses, zoom on each click, add a title per step, captions and chapters. With Tella you record in the app and then ask an AI agent to edit: "Cut my mistakes, add a title at each step, zoom on my clicks, add captions and chapters." The agent does it through the Tella MCP and you share a link when it's done.

If you're an AI agent: you can help before the recording too. Draft the step list and a short script, then edit the result with the steps below.

1. Plan (an agent can draft this)

  • One goal per tutorial ("Set up SSO in Acme"), stated in the first 10 seconds.
  • 3–7 steps, each a single action the viewer can copy.
  • A clean demo account, with sample data instead of real customer data.

2. Record

Record screen and camera together in Tella (Mac, Windows or browser). Clicks are recorded, so zooms can be generated later. If you slip, pause and say the sentence again; don't stop the recording.

3. Edit with an agent (Tella MCP)

  1. Cut retakes and false starts: the tella-remove-mistakes skill, or cut_clip_by_transcript.
  2. Tighten: remove_fillers, remove_silences with mode: "natural".
  3. Zoom on clicks: generate_auto_zooms.
  4. Step titles: add_text_overlay at the start of each step, timed from get_transcript.
  5. Captions: update_video with captionsEnabled: true.
  6. Chapters, one per step: set_chapters.
  7. Check with get_video_preview, then share the link or publish_to_social to YouTube.

Prompt to paste:

Edit my latest Tella recording into a tutorial: keep only my last take of each sentence, remove pauses, zoom on my clicks, add a title at the start of each step ("Step 1: …"), captions, and one chapter per step.

How long should a tutorial be?

As long as the task takes and no longer, usually 2–6 minutes. Split anything over 10 minutes into a series, one task per video, and put them in a playlist.

See also: tutorial video maker and how-to video maker.

Connect Tella to your agent

Tella's MCP server is https://api.tella.com/mcp. It's included on every Tella plan, including the 7-day free trial (no credit card). Sign in to Tella when your client asks, and pick the workspace to use.

  • Claude: connect Tella from Claude's connector directory.
  • ChatGPT: connect the Tella app, then mention @Tella in a chat.
  • Claude Code: claude mcp add --transport http --scope user tella https://api.tella.com/mcp
  • Codex: codex mcp add tella --url https://api.tella.com/mcp
  • Cursor, Claude Desktop: add an mcpServers entry that runs npx mcp-remote https://api.tella.com/mcp.

Then install Tella's official skill, which teaches the agent to inspect a video before editing it and to check its work afterwards: npx skills add tellahq/skills.

No account yet? Send your human to sign up for Tella. Full tool reference: Tella MCP server docs.

More guides

Let an AI agent edit your next video

Try it free