# Synthesia MCP > Synthesia MCP lets you generate professional, corporate AI avatar videos from text prompts directly via your agent. You can programmatically pull templates, list available avatars and voices, or automatically dub existing media into new languages without leaving your terminal. ## Overview - **Category:** ai-frontier - **Price:** Free - **Tags:** ai-video, synthetic-media, avatar-generation, video-dubbing, content-creation ## Description Need to build training modules or internal comms video? This MCP connects your conversational client to the Synthesia platform, turning your AI assistant into a virtual studio director. Instead of logging into a web portal and manually managing renders, you tell your agent what you need. It handles everything from listing available avatars to creating entire videos using pre-set templates with simple data payloads. You can even take an existing video and use the `dub_video` tool to instantly translate it into dozens of languages. By connecting this MCP through Vinkius, you give your agent operational access to a professional video pipeline. Your workflow goes from concept to final rendered file—all within the chat interface. This means corporate training leads can dispatch bulk instructional videos and localization teams can rapidly scale their video catalogs without ever touching a graphical user interface. ## Tools ### create_avatar_video Generates a new video file using a text script and a selected AI avatar. ### create_video_from_template Builds a video by populating the variables within an existing, defined template structure. ### get_video_details Retrieves the current status and detailed metrics for any specific video render. ### list_videos Fetches a list of all videos currently stored in your account. ### delete_video Permanently removes a designated video file. This action cannot be undone. ### list_avatars Returns an inventory of all professional AI avatars available to use in videos. ### list_templates Provides a catalog of video templates you can choose from for creation. ### get_template_details Retrieves the specific structure and variable requirements for any chosen template. ### list_voices Lists all available AI voice models, including language codes and accents. ### dub_video Translates and dubs an existing video into a new target language while keeping the original avatar. ## Prompt Examples **Prompt:** ``` Give me a list of internal AI video templates, select one related to 'customer support', and execute a creation pass using proper test inputs. ``` **Response:** ``` Accessing Synthesia directories ('list_templates')... Found template 'Support Starter' (ID: tmpl-1234). Fetching target blueprint variables natively ('get_template_details'). Dispatching 'create_video_from_template' with payload values successfully... Video task submitted. The ID is 'vid-5678'. Let me know when you want to execute 'get_video_details'. ``` **Prompt:** ``` List the available AI avatars, focusing on professional corporate styles. ``` **Response:** ``` Querying Synthesia avatar registry ('list_avatars')... Here are some of the active top corporate avatars available for rendering: 1. 'Anna_Business' (ID: 101) - Blazer, formal. 2. 'Marcus_Exec' (ID: 105) - Suit, authoritative. 3. 'Elena_Office' (ID: 112) - Smart casual, friendly. ``` **Prompt:** ``` Check the status of my recent video task 'vid-9920'. ``` **Response:** ``` Evaluating task bounds ('get_video_details')... The render for 'vid-9920' is COMPLETE. Total duration: 45 seconds. You can download and stream the final file here: `https://synthesia.io/stream/vid-9920_xyz`. ``` ## Capabilities ### Generate Videos from Script Creates an AI avatar video based on text you provide. ### Use Pre-Built Templates Generates a video by filling in the blanks of a specific, pre-designed template. ### Manage Video Statuses Checks if a video render is finished or deletes old drafts completely. ### Find Avatars and Voices Lists all available professional avatars and voice models for selection. ### Automate Localization & Dubbing Takes an existing video and automatically dubs it into different languages using native voices. ## Use Cases ### Updating Global Compliance Training A L&D specialist needs to update a core compliance video for 12 different international offices. Instead of manually re-recording the content twelve times, they run the original video through `dub_video` using the available voice list and get localized masters instantly. ### Launching New Product Onboarding An internal comms engineer needs to launch a new product training module. They first use `list_avatars` to pick a professional face, then select a template using `create_video_from_template`, and finally generate the video using `create_avatar_video` all in one go. ### Cleaning Up Old Media Assets A content manager finds dozens of old draft videos cluttering their account. They simply prompt their agent to list all files via `list_videos`, and then call `delete_video` on the junk, keeping only the finalized work. ### Developing Multi-lingual Marketing Assets A marketing team needs a video promoting a new feature in five languages. They use `list_voices` to select high-quality voices, and then trigger `dub_video` against their master source file for rapid global deployment. ## Benefits - You eliminate manual platform switching. Instead of jumping between a CMS and the video tool, your agent handles avatar generation and rendering entirely within the chat interface. - Scaling global content is simple. Using `dub_video`, you can take one core training module and instantly generate accurate versions in dozens of languages—no human translator needed for dubbing. - Template consistency matters. With `list_templates` and `get_template_details`, you ensure every video follows corporate branding guidelines, without manual checks. - You maintain control over your assets. You can check the status using `get_video_details` or clear out old drafts instantly with `delete_video` to keep things tidy. - Creating variety is fast. If a script changes, you don't rebuild from scratch; you just use `create_avatar_video` and feed it new text. ## How It Works The bottom line is you give your AI client the necessary keys; it handles the complex API calls for you. 1. Append the Synthesia MCP module to your Vinkius connective logic rules. 2. Pass your specific account authorization key (tied to Creator plans or beyond) to the host configuration. 3. Tell your agent exactly what to do, like listing all avatars and then generating a video saying 'Welcome' in Portuguese. ## Frequently Asked Questions **How do I generate an avatar video using the Synthesia MCP?** You use `create_avatar_video` and provide a script. This tool generates the video ID which you can then track for completion. **Can the Synthesia MCP dub videos into multiple languages?** Yes, using `dub_video`, you can take an existing recorded video and automatically translate and generate versions in different target languages. **What if I want to use a specific corporate layout?** Use `list_templates` first to see available layouts, then select one and use `create_video_from_template` with your data payloads. **How do I check if my video finished rendering via Synthesia MCP?** Call the `get_video_details` tool. This provides the current status, total duration, and confirmation that the render is complete. **Does the Synthesia MCP require me to list avatars first?** No, but it's smart practice. Use `list_avatars` upfront so you know exactly which professional faces are available for your scripts.