# Rev.ai MCP for AI Agents AI Agent Connect > Rev.ai MCP lets you turn audio and video files into accurate text. You can submit media files, generate AI summaries, and create captions directly from your AI client. It handles the entire lifecycle, from transcription to final analysis, making it easy to turn raw recordings into organized data without leaving your workspace. ## Overview - **Category:** productivity - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_8mAs5Sblbrb5mUGJJRfEyGyrwQy1HbvowtnIJANN/ai-agent-connect - **Tags:** transcription, speech-to-text, audio-processing, ai-summaries, captions ## Description Imagine you have hours of raw interview footage or a pile of podcast recordings. Usually, you'd have to manually upload these to a web dashboard, wait for them to process, and then copy-paste the text into your notes or project management tools. With the Rev.ai MCP, your AI agent does the heavy lifting for you. You can point your agent at a file or a URL, and it handles the submission, tracks the progress, and grabs the final text or captions whenever they're ready. It even handles the tedious parts, like summarizing long meetings or pulling out key topics so you don't have to skim through everything. If you have specific technical jargon or unique names, you can feed it a custom vocabulary to make sure the transcription stays accurate. It's a way to turn messy audio into organized data without the manual friction. You can find this and thousands of other tools in the Vinkius catalog to keep your workflow moving. ## Tools ### get_captions Get SRT or VTT caption files for a completed job. This makes it easy to add subtitles to your video content. ### get_language_id_result See the identified language and the confidence score for an audio file. This helps you know if the transcription is likely to be accurate. ### get_sentiment_analysis_result View sentiment scores for a transcript. This helps you understand the emotional tone of a conversation. ### get_stt_job Check the current status and details of a transcription job. Use this to see if your file is still processing. ### get_topic_extraction_result See the list of topics and scores from a job. This helps you quickly identify the main points of a recording. ### list_stt_jobs See all transcription jobs from the last 30 days. This helps you keep track of your recent work history. ### list_vocabularies View your recent custom vocabulary lists. Use this to manage the terms you've submitted for better accuracy. ### submit_language_id_job Send a file to identify what language is being spoken. This is useful for processing multi-language content. ### get_transcript_summary Get a concise summary of a completed transcript. This saves you from having to read through the entire text. ### get_transcript Retrieve the full text of a completed job. This provides you with the complete written record of your audio. ### get_vocabulary Check the processing status of a custom vocabulary. Use this to see if your custom terms are ready. ### submit_alignment_job Send audio and text for forced alignment. This matches specific words to timestamps in the audio. ### submit_sentiment_analysis_job Send a transcript to get sentiment scores. This helps you analyze the mood of a conversation. ### submit_stt_job Send a media file or URL to start the transcription process. This is the primary way to start a new job. ### submit_topic_extraction_job Send a transcript to pull out key topics. This helps you organize long recordings into themes. ### submit_vocabulary Submit a list of custom words to improve accuracy. Use this for technical terms or unique names. ### delete_stt_job Permanently remove a completed or failed transcription job. Use this to keep your history clean. ### delete_vocabulary Remove a custom vocabulary from your account. Use this when you no longer need specific custom terms. ### get_alignment_result Get the aligned timestamps from a forced alignment job. This is useful for creating precise subtitles. ## Prompt Examples **Prompt:** ``` Transcribe this podcast episode: https://example.com/audio.mp3 ``` **Response:** ``` I've submitted the transcription job for your audio file. The Job ID is `abc-123`. I'll monitor the status for you and let you know as soon as it's ready. ``` **Prompt:** ``` Give me a summary of the transcript for job ID abc-123. ``` **Response:** ``` Here is the summary for job `abc-123`: **Key Discussion Points:** * **API Strategy:** The team discussed the move toward a more modular API. * **Timeline:** The Q3 release is targeted for late September. * **Budget:** A 10% increase in the infrastructure budget was approved. **Conclusion:** The project is on track, pending the final approval of the cloud migration plan. ``` **Prompt:** ``` List my transcription jobs from the last month. ``` **Response:** ``` I found 3 recent jobs in your history: | Job ID | Status | Date | | :--- | :--- | :--- | | `abc-123` | Completed | Oct 12 | | `def-456` | In Progress | Oct 14 | | `ghi-789` | Failed | Oct 15 | Which one would you like to check? ``` ## Capabilities ### Submit audio for transcription Send a media file or URL to your agent to start a high-accuracy transcription job. ### Get transcripts in multiple formats Retrieve the full text of a completed job in plain text or JSON format. ### Generate video captions Create SRT or VTT caption files for your video content automatically. ### Create instant summaries Get a concise summary of a completed transcript to save time on long recordings. ### Improve accuracy with custom vocabulary Submit specific phrases or technical terms to ensure the agent transcribes them correctly. ### Analyze sentiment and topics Extract the emotional tone and key discussion points from your transcribed text. ## Use Cases ### Creating captions for a long podcast A content creator asks their agent to turn a 60-minute podcast into captions. The agent uses submit_stt_job and then get_captions to provide a ready-to-use SRT file. ### Summarizing a series of research interviews A researcher provides 10 interview recordings. The agent uses submit_stt_job for each and then get_transcript_summary to create a table of key findings from all of them. ### Extracting topics from focus group audio A UX researcher wants to know what people are talking about. The agent uses submit_topic_extraction_job to identify the most frequent themes in the recording. ### Processing voice notes with specific jargon A developer has voice notes full of internal code names. They use submit_vocabulary first, then submit_stt_job to ensure every technical term is transcribed perfectly. ## Benefits - Get captions for videos without leaving your chat by using get_captions to pull SRT files. - Save hours on meeting notes by using get_transcript_summary to get a concise summary of any recording. - Improve accuracy for niche technical terms by using submit_vocabulary to teach the agent your specific jargon. - Analyze the mood of a transcript with submit_sentiment_analysis_job to see how people are feeling. - Keep track of your history easily using list_stt_jobs to see what you've transcribed over the last month. - Identify languages automatically with submit_language_id_job so you can handle global content with ease. ## How It Works The bottom line is you turn raw audio into usable text and summaries without leaving your AI chat. 1. Connect your Rev AI Access Token to the Connector in your client settings. 2. Provide a media URL or file path to your AI agent to start the job. 3. Receive the final transcript, summary, or captions directly in your chat. ## Frequently Asked Questions **Can Rev.ai MCP transcribe my podcast recordings?** Yes, it can. You can provide the audio URL or file to your agent, and it will handle the transcription process for you. **How does Rev.ai MCP handle video captions?** It can generate SRT and VTT caption files for your video content. This makes it easy to add subtitles to your videos automatically. **Can I use Rev.ai MCP for sentiment analysis?** Yes, it can. Once a transcript is finished, you can ask your agent to analyze the sentiment to see the emotional tone of the conversation. **Does Rev.ai MCP support custom vocabulary for technical terms?** It does. You can submit a list of custom phrases or unique names to ensure the agent transcribes your specific jargon accurately. **Can Rev.ai MCP summarize long meetings?** Yes, it can provide a concise summary of a completed transcript. This helps you get the main points without reading the entire text. **Is Rev.ai MCP good for multi-language support?** Yes, it can identify the language of an audio file and provide transcriptions for various languages, making it great for global content. **Can I delete old jobs with Rev.ai MCP?** Yes, you can use the Connector to permanently remove completed or failed transcription jobs to keep your history organized. **How can I check if my transcription job is finished?** Use the `get_stt_job` tool with your Job ID. It will return the current status, such as 'in_progress', 'transcribed', or 'failed'. **Can I get subtitles for my video files?** Yes! Once a job is 'transcribed', use the `get_captions` tool. You can specify the format as either 'srt' or 'vtt'. **How do I improve accuracy for industry-specific jargon?** You can use the `submit_vocabulary` tool to provide a list of custom phrases. This helps the AI recognize technical terms and unique names more accurately.