mcpField
M
Make Subtitles

Make Subtitles

github.com/gitroomhqCreative & media8353 installsUpdated 3d ago
Repository

About Make Subtitles

Make Subtitles is an agent-media skill that burns styled captions onto a vNext video. It can transcribe the video automatically with Whisper when no transcript is supplied.

Key features

  1. 01Burns captions onto a video
  2. 02Automatic transcription with Whisper
  3. 03Hormozi, TikTok, and minimal styles

Use cases

  1. 01Add captions to a video without a transcript
  2. 02Apply a chosen caption style to a video

MCP support

Exposes caption generation through the agent-media MCP server's `mcp__agent-media__make_subtitles` tool. The tool schema is published through `tools/list`.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/gitroomhq/agent-media --skill make-subtitles

After installing, type/make-subtitlesin Claude Code to confirm it loaded.

Details

From the project README

Make Subtitles

Burn TikTok / Hormozi-style captions onto any vNext video (R2-hosted). Auto-transcribes via Whisper when transcript is omitted. Styles: hormozi (default), tiktok, minimal.

When to use this

Call this skill when the user asks for the outcome described above. It runs on the agent-media vNext primitive runtime via the mcp__agent-media__make_subtitles MCP tool. Authentication is the user's existing agent-media Bearer token (issued by agent-media login).

How to call it

Preferred path: MCP tool mcp__agent-media__make_subtitles. Schema is auto-published via tools/list against the same MCP server, so don't restate the schema here — trust the server's response.

Fallback path: REST.

POST https://api.agent-media.ai/v1/skills/make_subtitles/run
Authorization: Bearer $AGENT_MEDIA_API_KEY
Content-Type: application/json
Idempotency-Key: <any unique string per intent>

{
  "video_url": "https://pub-...r2.dev/vnext/primitive-runs/<id>/simple-selfie.mp4",
  "style": "hormozi"
}

What it costs and how long it takes

  • Credits: 15
  • Wall time (typical): 20s
  • Deducted at submit; refunded on terminal failure.

Polling the result

GET https://api.agent-media.ai/v1/primitives/runs/<run_id>
Authorization: Bearer $AGENT_MEDIA_API_KEY

House rules baked into this skill

Source of truth

This file is auto-generated by scripts/generate-public-skill.ts from the registry at services/api-v2/src/skills/registry.ts. Do not hand-edit; CI rejects drift.

Comments

Markdown supported