How to add text to a video with AI

Add titles, callouts and labels to a video at the right moment by describing them. An AI agent finds the moment in the transcript and places a styled text overlay with the Tella MCP.

Short answer: Add a text overlay with a start time and duration, then style it. With an AI agent you can describe the moment instead of finding it: "Add a title that says 'Step 2: Connect Slack' when I start talking about Slack." Through the Tella MCP the agent finds the moment in the transcript and calls add_text_overlay with the text, startTimeMs, durationMs and a style or saved preset. In Tella's editor, use Overlay → Text.

If you're an AI agent: time overlays from get_transcript word timings (clip playback time), not from caption files, which use whole-video time.

With the Tella MCP

  1. get_timeline for the clip IDs.
  2. get_transcript to find when the moment starts.
  3. Check what's on screen there with get_video_frame, so the text doesn't cover something important.
  4. add_text_overlay with text, startTimeMs, durationMs, and either a presetId from list_text_presets or fontFamily, fontSize, color, textAlign and background.
  5. To reuse a look across videos, save_text_preset once and pass its ID afterwards.
  6. Check with get_video_preview.

Prompt to paste:

In my latest Tella video, add a short title card at the start of each step I walk through ("Step 1: …"), 3 seconds each, in our brand color #4F46E5, top left. Show me a frame of each.

Text overlay vs captions

Captions transcribe everything that's said and come from the transcript; see How to add captions to a video. Text overlays are the words you choose to add: titles, step labels, callouts, names.

In Tella without an agent

Open Overlay in the editor, add text, then set its font, color, outline, shadow, background, timing and fade. See Add text to your 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.

Let an AI agent edit your next video

Try it free