MCP server live at brains.subtitlesking.com/mcp

Subtitles for any video.
For humans, for agents.

Add AI-generated subtitles to any video in minutes. Hosted MCP server, REST API, and an open-source self-host binary — pick whichever fits your workflow.

Install in one line

claude mcp add --transport http subtitlesking https://brains.subtitlesking.com/mcp
Subtitles King mascot on a throne

Three ways to ship it

Pick the one that fits your stack.

Hosted MCP

No-install MCP

Register one URL in Claude Code, Claude Desktop, Cursor, or Windsurf. We host the server.

# Register the hosted MCP — no install
claude mcp add --transport http subtitlesking \
  https://brains.subtitlesking.com/mcp
See MCP →
Self-host

Your hardware, zero lock-in

Open-source Go binary. Run it on your laptop, your server, or behind your firewall.

# Run the open-source binary on your machine
curl -L https://github.com/kirillzubovsky/subtitlesking-mcp/releases/latest/download/subtitlesking-mcp-darwin-arm64.tar.gz \
  | tar -xz
sudo mv subtitlesking-mcp /usr/local/bin/

claude mcp add subtitlesking $(which subtitlesking-mcp)
Self-host →
REST API

Plain HTTP, plain JSON

No SDK required. curl, fetch, requests, net/http — whatever your stack speaks.

# Or just hit the REST API
curl -X POST https://brains.subtitlesking.com/presign \
  -H "X-API-KEY: $SK_API_KEY" \
  -d '{"filename":"clip.mp4"}'
See API →

Under the hood

One pipeline. Four steps. Open source.

Upload your video, we compress it, run OpenAI Whisper, then burn the subtitles back into the video with ffmpeg. The transcript is available as soon as Whisper finishes — usually a couple minutes before the burned video.

01
Upload
Multipart upload with a presigned URL.
02
Compress
ffmpeg downscales for fast Whisper passes.
03
Transcribe
OpenAI Whisper large model → SRT.
04
Burn
ffmpeg burns subtitles back into the video.

Bytes never enter the LLM

The MCP hands the agent a presigned URL. The agent uploads with curl, server-to-server. No base64-blasting your context window.

MCP-native, not bolted on

Built for AI agents from day one. Four tools that map cleanly to the upload → status → download lifecycle.

Self-host or hosted

Run our binary against your data, or use the hosted endpoint. Same tools, same protocol, your choice.

Plain HTTP

Two requests to subtitle a video.

Get a presigned URL, upload your file, get back an authToken. Poll /queue until your subtitled video is ready.

# 1. Get a presigned upload URL
curl -X POST https://brains.subtitlesking.com/presign \
  -H "X-API-KEY: $SK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"filename":"clip.mp4"}'

# 2. Upload your video
curl -X POST "$UPLOAD_URL" -F "file=@clip.mp4"

# → { "videoID": "...", "authToken": "12345678" }

Compared

The honest comparison.

See all comparisons
vsCostMCPSelf-hostLines to integrate
AssemblyAI$0.37/hr~25Compare →
Rev.ai$1.25/min~30Compare →
Deepgram$0.43/hr~20Compare →
Whisper self-hostedGPU $$~80Compare →
Subtitles KingFree / waitlist~3

Stop writing subtitle code.

Free tier supports videos up to 100 MB. No credit card. No signup. MCP-ready out of the box.