How do I let Cursor transcribe audio and video?

Add the KolWrite MCP server to ~/.cursor/mcp.json (or open the install link below). The Cursor agent can then transcribe recordings in your project into text, subtitles or translations, billed per second to your KolWrite credits.

Get an API key Quickstart Supported languages

Last updated: · Markdown

What you do once

Create the account and the key yourself at console.kolwrite.com: sign up, add credits, then open API Keys and create a key. An agent cannot do this for you.

Put the key in your shell profile (~/.zshrc, ~/.bashrc) so every agent session you start can read it, then open a new terminal:

export KOLWRITE_API_KEY=...   # paste the key from API Keys

The tools read the key only from this variable. Do not paste it into a chat or commit it to a repository.

Add the MCP server

In ~/.cursor/mcp.json (every project) or .cursor/mcp.json (one project). ${env:KOLWRITE_API_KEY} reads the key from the environment Cursor was started in:

{
  "mcpServers": {
    "kolwrite": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "https://console.kolwrite.com/mcp/kolwrite-mcp-0.1.0.tgz"
      ],
      "env": {
        "KOLWRITE_API_KEY": "${env:KOLWRITE_API_KEY}"
      }
    }
  }
}

Or open this link in a browser on the computer where Cursor is installed; Cursor asks before it adds the server: Add KolWrite to Cursor

The server gives the agent six tools: transcribe_file, transcribe_url, upload_file, get_job, list_models, list_languages. It runs on your computer with Node.js 18 or newer and is fetched from https://console.kolwrite.com/mcp/kolwrite-mcp-0.1.0.tgz (SHA-256 0dcd6ff169b860b9363044837b8545279efa585c4987b20d81035f920f6ac7ca).

If the tools do not show up, start Cursor from a terminal where KOLWRITE_API_KEY is set, or open Cursor Settings, MCP, and check the server status.

Keep a project rule

So the agent also knows the API when it writes code, add a rule in .cursor/rules/kolwrite.mdc:

---
description: Speech-to-text with the KolWrite API
alwaysApply: false
---
For speech-to-text use the KolWrite API; read https://console.kolwrite.com/agent-instructions.md first. The key is in KOLWRITE_API_KEY; never print it.

What to ask

Three things to ask the Cursor agent:

Transcribe ~/Downloads/interview.m4a with KolWrite and save the text as interview.txt next to it.

Make English SRT subtitles for talk.mp4 with KolWrite, one cue per sentence.

Who said what in team-call.mp3? Transcribe it with speaker labels on the oracle model, then list each speaker's action items.

What it costs

JobModelCost
A 30-minute interview, plain textbaseUS$0.24
A one-hour meeting with speaker labelsoracleUS$1.56
A one-hour Hebrew talk with English subtitlesoracleUS$1.44
One hour of noisy, overlapping audiooracle_maxUS$3.60

Billed per second of audio from your credits, with no minimum. Speaker labels add 0.10 credits per audio hour. The MCP server and kolwrite.py pick base unless you or the agent name another model, and oracle_mini when translating. Full rates: /models.

What the agent must not do

  • Ask you for the key in the chat, print it, or write it into a file, a command or a commit.
  • Start the same transcription again after a timeout or a network error. Each start is a new job that is billed; it should check the job instead, or ask you.
  • Type timestamps itself. To cut or quote by time it takes segment numbers from the transcript and computes the times in code from the word timings.
  • Send a YouTube or other web page address as the media. It needs the media file itself.
  • Transcribe long recordings (over an hour) without telling you the expected cost first.

Questions and answers

Does it work in Ask mode?

MCP tools run in the agent. Use the agent to transcribe; Ask mode can read the transcript afterwards.