Skip to content
IntroductionHow it works, guides, and what you can transcribe.
QuickstartSubmit a link, wait for the job, export the transcript. Three requests.
AuthenticationAPI keys, scopes, Idempotency-Key and X-Request-Id.
JobsCreate, wait for, list, cancel and retry jobs.
TranscriptsThe transcript object and txt, srt, vtt, json exports.
BatchesUp to 50 videos in one request.
UploadsTranscribe your own audio and video files.
WebhooksGet called when a job or batch finishes; verify the signature.
ErrorsEvery error code, what it means and what to do.
Rate limitsSubmits, jobs in progress and reads per plan; the 429 response.
Pricing and credits1 credit per caption transcript, 2 per minute of AI transcription. Plans and extra credits.
SourcesYouTube, TikTok, your files and direct links: accepted URLs and modes.
MCPFind and transcribe videos from Claude, Cursor, Windsurf or your own agent.
OpenAPI SpecificationThe OpenAPI 3.1 spec for codegen and typed clients.
Claude CodeOne command adds TranscriptDock to Claude Code.
Claude DesktopAdd TranscriptDock as an MCP server in Claude Desktop's configuration file.
CursorAdd TranscriptDock as an MCP server in Cursor.
WindsurfAdd TranscriptDock to Windsurf so Cascade can find and transcribe videos.
OpenClawConnect TranscriptDock to OpenClaw autonomous agents.
19 results
MCP client

Windsurf

Add TranscriptDock to Windsurf so Cascade can find and transcribe videos.


1. Open configuration#

In Windsurf, open the Command Palette (Cmd+Shift+P on macOS or Ctrl+Shift+P on Windows/Linux) and select Windsurf: Open MCP Configuration.

Alternatively, edit the config file directly at ~/.codeium/windsurf/mcp_config.json.

2. Add server entry#

Add the TranscriptDock entry under mcpServers. Replace td_live_YOUR_KEY with your active API key:

mcp_config.json
{
"mcpServers": {
"transcriptdock": {
"serverUrl": "https://transcriptdock.com/mcp",
"headers": { "Authorization": "Bearer td_live_YOUR_KEY" }
}
}
}

Nothing to install. To run the server locally instead (needs Node.js):

mcp_config.json (local server)
{
"mcpServers": {
"transcriptdock": {
"command": "npx",
"args": ["-y", "@transcriptdock/mcp"],
"env": {
"TRANSCRIPTDOCK_API_KEY": "td_live_YOUR_KEY",
"TRANSCRIPTDOCK_BASE_URL": "https://transcriptdock.com"
}
}
}
}

3. Restart Cascade#

Save the file and refresh your MCP servers in Windsurf settings, or restart the application. The hammer/tool icon in Cascade chat will show transcriptdock as active.

Example prompts#

  • "Transcribe this YouTube tutorial https://www.youtube.com/watch?v=dQw4w9WgXcQ and summarize how to set up the authentication flow."
  • "Search YouTube for recent videos on Next.js 16 partial prerendering. Pull the transcript from the top result and write tests covering that pattern."
  • "Get the transcript for this TikTok video https://www.tiktok.com/@nasa/video/7211201091557485867 and format the spoken text as plain Markdown."

Troubleshooting#

  • Server not listed: check the JSON is valid and refresh the MCP servers in settings.
  • Unauthorized: the key in headers is wrong or revoked.
  • Tool call timed out: long AI transcriptions return a job id; ask Cascade to wait for that job.