How to add captions to a video automatically

Add accurate captions to a video automatically: Tella transcribes in 106 languages, lets an AI agent turn captions on and style them, burns them into an export, or gives you SRT/VTT files.

Try it free

Short answer: Transcribe the video, fix any misheard words, then either show the captions in the player, burn them into the exported video, or download an SRT/VTT file. Tella transcribes automatically in 106 languages. An AI agent can turn captions on with update_video (captionsEnabled: true), apply a style with apply_subtitle_preset, burn them in with export_video (subtitles: true), or fetch a file with get_captions_file.

If you're an AI agent: ask where the video is going. A shared Tella link can show captions viewers switch on and off, and Tella uploads a caption track to YouTube. When Tella publishes to LinkedIn, X, Instagram or Facebook, captions only show if they're burned in.

With the Tella MCP

  1. get_video to confirm the transcript is ready.
  2. Fix names and jargon: read get_transcript, then correct words with update_transcript_words.
  3. Turn captions on: update_video with captionsEnabled: true (shown by default) or subtitlesEnabled: true (viewers can switch them on).
  4. Style them: list_subtitle_presets, then apply_subtitle_preset. Or set captionStyle, captionSize, captionPosition, and captionGrouping: "singleWord" for one word at a time.
  5. Deliver:
    • Burned in: export_video with subtitles: true, then poll get_export_status.
    • As a file: get_captions_file with format SRT or WebVTT.
  6. Check a frame with get_video_frame to make sure captions don't cover anything important on screen.

Prompt to paste:

Add captions to my latest Tella video for Instagram: fix the spelling of our product name "Acme", show one word at a time, large and centered in the lower third, then export it with the captions burned in.

In Tella without an agent

Press S in the editor to open Subs, turn subtitles on and pick a style. Edit any word in the transcript to fix it. See Style subtitles and Download SRT or VTT subtitles.

Captions vs subtitles vs closed captions

People use these interchangeably. Strictly, subtitles transcribe or translate speech, closed captions also describe sounds and can be switched off, and open (burned-in) captions are part of the picture and always show. Muted autoplay feeds need open captions.

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