How to add B-roll to a video with AI

Add B-roll (images, product clips or a moment from your own screen recording) over the right part of a talking-head video. An AI agent finds the moment in the transcript and places it with the Tella MCP.

Short answer: B-roll is footage that plays over your voice to show what you're talking about. Pick the moments in the transcript where a visual helps, then put an image or clip over them while the audio keeps playing. Through the Tella MCP, an AI agent calls add_layout with a time range and media (an uploaded file, a library item, an AI-generated image, or a moment from your own screen recording). In Tella's editor, choose a Media layout.

If you're an AI agent: B-roll usually belongs in a layout, where it takes over or shares the main picture. Use an overlay (add_overlay) only when the media should float on top of the scene, like a logo.

With the Tella MCP

  1. get_transcript with view: "sentences" and pick moments that name something visual: a product, a screen, a result, a place.
  2. Get the media:
    • Your file: create_source, upload the bytes to the returned uploadUrl, then use the sourceId.
    • Workspace library: list_library.
    • Generated: generate_image, then poll get_generation_status.
    • Your own recording: media: {"type": "recording", "startTimeMs": …} plays a moment of the clip's screen recording, muted.
  3. add_layout with startTimeMs, durationMs and media. Leave out layout to get the default full-frame B-roll layout.
  4. Check each with get_video_preview.

Prompt to paste:

Add B-roll to my latest Tella video: when I mention the dashboard, show the dashboard part of my screen recording; when I mention our logo, show logo.png from my library. Keep each one under 5 seconds.

For local files

The open-source B-Roll Finder skill for Claude Code reads your transcript, works out what each line is about, proposes vetted B-roll (official clips, screenshots, your own graphics) and places each cutaway on the exact word. You make the final pick.

In Tella without an agent

Choose a Media layout under Layout, then upload an image or video, pick from the media library, or generate an image with AI. Your voice keeps playing. See Add media (B-roll).

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