# 3Scribe MCP MCP > 3Scribe: Automated transcription for audio and video files. This MCP lets your AI client manage the entire media processing lifecycle, from submitting a public URL to checking job status and retrieving text transcripts. It handles everything needed for turning spoken word into structured, searchable data without manual intervention. ## Overview - **Category:** productivity - **Price:** Free - **Tags:** transcription, speech-to-text, audio-processing, video-transcription, automated-jobs, media-analysis ## Description Turning hours of recorded speech—whether it's meeting audio or video footage—into usable text used to be tedious. Now, your agent handles the whole process. You simply point your client at a media file URL and tell it what you need. The system takes care of creating the job, monitoring its progress in real time, and finally pulling out the raw transcript. It’s like having a dedicated transcription service built right into your workflow. If you're building complex systems that deal with media data, connecting 3Scribe via Vinkius gives your agent access to this core functionality, making it easy for any compatible AI client to manage jobs and retrieve detailed word-level text. ## Tools ### create_job Submits a public media URL to start the transcription process and returns a job ID. ### list_jobs Gets a paginated list of all your current and past transcription tasks in the account. ### get_job Checks the status of a job ID and retrieves the full text transcript if processing is complete. ### delete_job Permanently removes a specific transcription task and all associated data from your account. ## Prompt Examples **Prompt:** ``` Transcribe the audio from this URL: https://example.com/podcast.mp3 ``` **Response:** ``` I've started a new transcription job for your podcast. The Job ID is 12345. You can check the status in a few minutes using the `get_job` tool. ``` **Prompt:** ``` What is the status of my transcription job 54321? ``` **Response:** ``` Checking job 54321... The status is 'Completed'. Here is a summary of the transcribed text: [Summary...] ``` **Prompt:** ``` Delete my old transcription job with ID 99999. ``` **Response:** ``` I've successfully deleted the transcription job 99999 from your account. The data has been permanently removed. ``` ## Capabilities ### Initiate Transcription Jobs Submit a public URL for an audio or video file to start the automated transcription process. ### Track Job Status Check if a job is pending, processing, completed, or failed using the assigned job ID. ### Fetch Final Transcripts Retrieve the full text transcript, including detailed timestamps and speaker identifications. ### Manage Job Records List all existing transcription jobs or permanently delete old job data to keep records clean. ## Use Cases ### Capturing Podcast Content The marketing team needs captions for a new podcast episode. Instead of uploading files to a separate service, the agent uses `create_job` with the public URL and later calls `get_job` to pull the finalized transcript text for the website. ### Auditing Old Records A compliance officer needs to audit all historical meeting recordings. The agent first runs `list_jobs` to get a full manifest, then filters by status and deletes unnecessary projects using `delete_job`. ### Analyzing Interview Data A researcher records several interviews. They use `create_job` for each one. Later, they check the status of all jobs with `get_job` to ensure data is ready before pulling it into their database. ### Batch Processing Media A developer needs to process 50 video files simultaneously. They use `list_jobs` to track the progress of all submissions and can manually trigger checks on specific IDs using `get_job` until everything is marked 'Completed'. ## Benefits - Stop manually transcribing. By calling `create_job`, your agent handles the media ingestion and job setup using just a public URL, saving hours of copy-paste work. - Get detailed data points, not just blocks of text. The system allows retrieval of word-level data with timestamps and speaker IDs via `get_job` for forensic accuracy. - Maintain clean records. Use `list_jobs` to see all your media tasks at a glance, and when you're done with an old project, use `delete_job` to wipe the record completely. - Flexible Language Handling. You can either specify the language type or let the system auto-detect the spoken language before initiating the job via `create_job`. - Workflow Automation. Instead of building a dedicated media API client, your agent handles this entire workflow using simple natural language commands across all four tools. ## How It Works The bottom line is, you just hand over the link, and your agent handles the entire lifecycle: starting, tracking, and finishing the process for you. 1. Start by providing the MCP with a public URL pointing to your audio or video file. 2. The system creates a unique Job ID and begins processing the media content automatically. 3. You use that Job ID later to check the status, retrieve the raw text, or delete the record. ## Frequently Asked Questions **How do I start a transcription job using the create_job tool?** You provide the MCP with a valid public URL to the audio or video file. The system takes that URL, creates a unique Job ID for you, and starts processing it automatically. **What should I use if I need to check the status of my transcription job?** You must use `get_job`. You'll supply the specific Job ID that was returned when you initially created the task. This tool checks the current state and pulls the text if done. **Can I delete all my old jobs at once?** No, not directly. First, run `list_jobs` to see what IDs exist. Then, you must call `delete_job` for each specific Job ID you want to permanently remove. **Does the 3Scribe MCP handle video and audio?** Yes, it handles both types of media equally well. The system accepts a public URL whether that file is an MP3 or an MP4, provided it's accessible. **If I run into an issue with a transcription, how does the `get_job` tool help me troubleshoot?** The `get_job` tool returns specific status codes and error messages when something goes wrong. If a job fails, you'll get details telling you if it was due to a bad URL or an internal processing fault. **Does the `list_jobs` command allow me to filter tasks by their current processing status?** Yes. The tool retrieves all jobs, but your agent can narrow down that list using filters. You can target specific statuses like 'Error' or 'Processing' without having to review every single record. **What format does the text output from `get_job` use for highly detailed data?** The raw text transcript retrieved by `get_job` includes rich metadata. You get timestamps for every segment, and it separates content using speaker IDs so you know exactly who said what. **What happens if I try to run a job with an invalid public URL via the `create_job` tool?** The system validates the provided public media URL before starting. If the link is inaccessible or improperly formatted, the agent will receive an immediate error notification, preventing any attempt to start a failed job. **How do I start a new transcription?** Use the `create_job` tool and provide the public URL of your audio or video file. Your agent will initiate the process and provide a Job ID. **Can I check if a transcription is finished?** Yes. Use the `get_job` tool with the Job ID. It will return the current status and, if completed, the transcribed text. **How can I clean up my transcription history?** Use the `delete_job` tool and provide the Job ID. This permanently removes the transcription data from your 3Scribe account.