Transcribe Video API

Skill

Install the agent skill so your AI assistant can transcribe for you.

The agent skill teaches an AI coding agent (Claude Code, Codex, Cursor) how to transcribe media using the transcribe CLI — including how to handle speaker labels, languages, and locked previews.

Install

npx skills add adiIspas/transcribevideototext-agent

Then ask your agent, in plain language:

Transcribe ./interview.mp4 and give me the dialogue with speaker labels.

How it works

The skill uses the transcribe CLI under the hood. On first use it ensures the CLI is installed and checks that you are authenticated (transcribe login, or a VTT_API_KEY in the environment).

Prefer tools over a CLI? The same capabilities are available through the MCP server.

On this page