# Verbit MCP MCP > Verbit handles professional transcription and captioning for media files. Just give your agent a link, and it manages the entire job: uploading the audio/video, tracking its progress in real time, and finally downloading the complete transcript or captions in formats like SRT, VTT, or DOCX. ## Overview - **Category:** productivity - **Price:** Free - **Tags:** transcription, speech-to-text, captioning, accessibility, media-processing ## Description Verbit lets you turn any piece of recorded media into usable text. Instead of manually managing separate transcription services, your agent handles the whole pipeline—from start to finish. You feed it a public URL for an audio file; it starts the job and monitors its progress until it's done. Once complete, you get the full transcript or captions ready to use in any format you need, like JSON or Word. The platform runs these complex workflows safely inside Vinkius’s isolated sandbox, guaranteeing that your API keys pass through a zero-trust proxy and never sit on disk. This means you can focus solely on getting high-quality text output without worrying about secure credential management. ## Tools ### create_job Starts a new job by submitting a media file URL that needs to be transcribed. ### get_job Checks the current status and progress of an existing transcription job ID. ### get_transcript Retrieves the final, completed transcript for a given job ID in your preferred format. ## Prompt Examples **Prompt:** ``` Create a transcription job for this audio file: https://example.com/interview.mp3 ``` **Response:** ``` I've started the transcription job for your file. The Job ID is 'vbt_98765'. You can check its progress anytime. ``` **Prompt:** ``` What is the current status of Verbit job vbt_98765? ``` **Response:** ``` Checking the status... Job 'vbt_98765' is currently at 75% progress and is in the 'In Progress' state. ``` **Prompt:** ``` Download the transcript for job vbt_98765 in Word format. ``` **Response:** ``` I've retrieved the transcript for job 'vbt_98765' in DOCX format. You can access the content here. ``` ## Capabilities ### Initiate transcription jobs You give the agent a media URL, and it starts processing the file for text output. ### Track job status updates The agent checks the system to tell you if your transcript is pending, in progress, or finished. ### Download completed transcripts Once a job finishes, the agent fetches and delivers the text file in various structured formats. ### Tag jobs with external IDs You link your Verbit transcript job to an ID you already use in your internal project management system. ## Use Cases ### Post-Interview Documentation A legal team uploads multiple interview recordings. The agent first uses `create_job` for all files, then loops through them using `get_job` until they are all complete, finally calling `get_transcript` to pull all required DOCX files into a single folder. ### YouTube Captioning Pipeline A content creator uploads a new video link. The agent calls `create_job`, waits for the job ID, and when done, uses `get_transcript` to pull the SRT file directly into their asset management system. ### Project Status Reporting A product manager needs a report on 50 different videos. They call `create_job` for all of them, and then use `get_job` in a batch loop to confirm which ones are ready before pulling the final JSON data with `get_transcript`. ### Historical Archiving An academic needs to archive historical audio. They run `create_job` and tag it with an internal archival ID, ensuring that when they use `get_transcript`, the output is perfectly linked back to their source records. ## Benefits - You get immediate captions (SRT/VTT) for videos. No more manually exporting and timing caption files; just ask the agent to create them. - The workflow is fully traceable. You can use external IDs when creating a job, linking the transcript directly back to your internal project tracking system. - You don't get stuck on single formats. The agent pulls transcripts in multiple file types—JSON, TXT, DOCX, and more—so you never have to re-save anything. - It manages status checks automatically. You can use the `get_job` tool repeatedly until your workflow confirms that the transcript is ready for download. - The entire process is secure. All API calls run through Vinkius's zero-trust proxy, meaning your Verbit keys pass in transit but never sit on disk. ## How It Works The bottom line is: your AI client manages the entire waiting period and data transfer between Verbit's service and your final output. 1. First, tell the agent which media file needs transcribing by providing a public URL. 2. Next, the agent uses that information to start the job and then periodically checks its status until it reports completion. 3. Finally, you ask the agent for the transcript, specifying the required format (e.g., SRT or DOCX), and it retrieves the finished file. ## Frequently Asked Questions **How do I start a transcription job with Verbit?** You initiate the process by calling `create_job` and providing the public URL of the media file you want transcribed. This kicks off the entire background process. **Can I check the progress using the Verbit MCP?** Yep. You use the `get_job` tool, giving it your unique job ID. It tells you exactly what percentage of completion the job is at and its current status. **What file formats can I get from Verbit?** You can download transcripts in many formats. The `get_transcript` tool supports JSON, TXT, SRT, VTT, DOCX, and more, so you only get what your downstream system needs. **Does the Verbit MCP handle large files?** Yes. It's designed for professional media processing, allowing you to manage high-quality speech-to-text tasks even with long or complex audio inputs. **What credentials do I need to successfully run `create_job` with Verbit?** You must provide your Verbit API Key. This key connects your agent securely to the platform and is handled by Vinkius's zero-trust proxy. Your keys are never stored on disk, ensuring secure access for every job you create. **Can I use `create_job` to tag my media files with external IDs?** Yes, you can assign custom external IDs when using `create_job`. This feature is key for maintaining consistency and linking the transcription job back to records in your internal database or project management tools. **If I run `get_transcript`, what should I do if the file download fails?** First, check the status using `get_job`. A failed retrieval often means the job hasn't hit 100% completion yet. Wait until the status shows 'Completed' before attempting to download the transcript again. **Does the Verbit MCP support chaining all three tools (`create_job`, `get_job`, and `get_transcript`)?** Absolutely. You can chain these calls together within your agent workflow. For example, the Job ID generated by `create_job` is automatically passed to `get_job` and subsequently used for `get_transcript`. **How do I start a new transcription job using a video link?** Use the `create_job` tool. Simply provide the `file_url` of your media and optionally specify the `language` and a `title` to identify the job later. **Can I download subtitles for my video in SRT format?** Yes! Once the job is finished, use the `get_transcript` tool with your `job_id` and set the `format` parameter to 'srt'. **How can I check if my transcription is already finished?** You can use the `get_job` tool. By providing the `job_id`, the agent will return the current status and progress percentage of your transcription.