# GetTranscribe — how to use (mcp.ai)

Connect your GetTranscribe account and use 9 tools for transcription straight from your AI agent. Connect with your own API key. GetTranscribe converts supported video and media URLs into searchable transcriptions and provides tools for managing transcription jobs, results, and folders.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_get_transcribe?ms=1787291340000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `get_transcribe_create_transcription_job`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/get_transcribe`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/get_transcribe/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/get_transcribe/create/transcription/job` — Queue a paid asynchronous transcription job for a supported public video or direct media URL. Returns a job ID to poll with Get Transcription Job; this operation can consume transcription credits.
  - body: { url: string, model?: string, prompt?: string, language?: string, folder_id?: integer }
- `POST https://api.mcp.ai/api/get_transcribe/get/current/account` — Return the connected GetTranscribe account's safe identity, plan, usage limits, and available balances.
- `POST https://api.mcp.ai/api/get_transcribe/get/folder` — Retrieve one transcription folder owned by the connected account.
  - body: { folder_id: integer }
- `POST https://api.mcp.ai/api/get_transcribe/get/transcription` — Retrieve one completed transcription with its text and media metadata; optionally include potentially large word and segment timing arrays.
  - body: { transcription_id: integer, include_timing_data?: boolean }
- `POST https://api.mcp.ai/api/get_transcribe/get/transcription/job` — Get the status and progress of one asynchronous transcription job, including the finished transcription ID or failure details.
  - body: { job_id: integer }
- `POST https://api.mcp.ai/api/get_transcribe/list/folders` — List transcription folders owned by the connected account, optionally filtering by parent folder.
  - body: { limit?: integer, parent_id?: integer, sort_order?: integer, next_cursor?: string }
- `POST https://api.mcp.ai/api/get_transcribe/list/transcription/jobs` — List asynchronous transcription jobs for the connected account, optionally filtered by lifecycle status.
  - body: { limit?: integer, status?: string, sort_order?: integer, next_cursor?: string }
- `POST https://api.mcp.ai/api/get_transcribe/list/transcriptions` — List lightweight completed-transcription metadata for the connected account, with folder and platform filters.
  - body: { limit?: integer, platform?: string, folder_id?: integer, sort_order?: integer, next_cursor?: string }
- `POST https://api.mcp.ai/api/get_transcribe/resolve/media/download/url` — Resolve a fresh direct download URL for supported social or direct media without creating a transcription. This paid request may consume provider credits, and returned URLs can expire.
  - body: { url: string }

## Example prompts
- "What can I do in GetTranscribe?"
- "Show me a summary of my GetTranscribe account"

## More
- Page: https://mcp.ai/get_transcribe
- Agent spec (llms.txt): https://mcp.ai/get_transcribe/llms.txt
- Postman collection: https://mcp.ai/get_transcribe/postman.json