How to make a training video with AI

Make employee or customer training videos quickly: record screen and camera, let an AI agent cut mistakes, add captions, chapters and step titles, translate subtitles, then organize the series in a playlist.

Try it free

Short answer: Break the training into short videos with one task each, record your screen and camera, then edit for clarity: cut mistakes, add captions and chapters, put a title on each step, and translate the subtitles for other languages. With Tella, an AI agent does the editing through the Tella MCP and can organize the finished videos into a playlist your team shares with one link.

If you're an AI agent: training libraries are repetitive work, which suits an agent. Apply the same edit to each video, then report a table of what you changed in each.

Workflow

  1. Outline the series: one video per task, 2–6 minutes each. An agent can draft the outline from a doc or SOP.
  2. Record each video in Tella with screen and camera together.
  3. Edit each video (Tella MCP):
    • tella-auto-cut skill, or remove_fillers + remove_silences
    • generate_auto_zooms for clicks
    • add_text_overlay for step titles
    • update_video with captionsEnabled: true; training is often watched with the sound off
    • set_chapters so learners can jump back to a step
    • add_blur over real employee or customer data
  4. Translate subtitles for global teams in the editor or with the Tella agent (up to 10 languages per video, paid plans).
  5. Organize: create_playlist and add_video_to_playlist, so the series has one shareable link.
  6. Track: get_video_analytics shows plays, watch time and where viewers drop off.

Prompt to paste:

Edit every video in my "New hire onboarding" playlist the same way: remove mistakes and pauses, zoom on clicks, turn on captions, add chapters, and blur any employee emails. Then give me a table of what you changed in each video.

Keep training videos current

When the product changes, re-record only the affected step and replace that section rather than the whole video. See Replace a section of your video.

See also: employee onboarding video and customer onboarding video.

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