# Fliki MCP > Fliki (AI Text-to-Video & Speech API) is your connector for creating full video content from simple text scripts. It lets you generate videos using customizable voices, set aspect ratios, and add background music, all without manual editing. You can also check on the status of large batches and explore a list of available global AI voices to pick the perfect accent or language. ## Overview - **Category:** image-video - **Price:** Free - **Tags:** text-to-video, text-to-speech, ai-video, content-creation, multimedia ## Description Turn raw text into finished video content using this MCP connector. Your agent handles the whole process: from picking the right voice to generating the final, shareable file. You give it a script; you tell it if you need a vertical clip for Instagram or a wide format for YouTube. It figures out the voices and settings, then it builds the video, complete with background music tracks. If your project requires complex multimedia production, Vinkius's catalog makes connecting Fliki easy. Once the task is running, you don't have to wait; you can check back in later to see if it finished or if there are any issues. ## Tools ### generate_video Creates a new video file using the text script you provide and optional voice, aspect ratio, and music settings. ### get_video Retrieves the current status of a generation job and provides a direct download link if the video is finished. ### list_voices Returns an organized list detailing all available AI voices and which languages they can speak. ## Prompt Examples **Prompt:** ``` Show me the available AI voices and their languages. ``` **Response:** ``` I've retrieved the list of voices. You can choose from 'Sara' (English), 'Joao' (Portuguese), 'Elena' (Spanish), and many others. Which language or style are you looking for? ``` **Prompt:** ``` Generate a 9:16 video for TikTok with the script: 'Top 3 productivity tips for developers' using the voice 'Sara'. ``` **Response:** ``` I've started the video generation for your TikTok script. The task ID is 'flk_v8291'. I will monitor the progress and let you know when the download link is ready. ``` **Prompt:** ``` Check the status and get the download link for video ID 'flk_v8291'. ``` **Response:** ``` The video generation for 'flk_v8291' is now 'completed'. You can download your video here: [https://fliki.ai/download/v8291]. ``` ## Capabilities ### Create videos from text Write a script and generate an entire video file, selecting voices, background music, and the required aspect ratio. ### Monitor generation status Check if a requested video is queued, processing, or ready for download, getting a public link when it's done. ### List all available voices Pull a list of every voice option and the languages they support so you can pick the right tone for your content. ## Use Cases ### Need a rapid series of social ads A marketing team needs five variations of a product ad for different platforms (Instagram Reel, YouTube Short). They use `list_voices` to pick three tones, then call `generate_video` five times with the same script but varying the aspect ratio and voice parameters. ### Publishing an e-book chapter An author writes a chapter transcript. Instead of hiring a narrator and editor, they use `generate_video` to convert the text immediately into a polished video module for their online course. ### Checking on a large campaign batch After submitting 50 videos via `generate_video`, an agent uses `get_video` repeatedly. It confirms which videos are still processing and alerts the user only when all download links are active. ### Localizing global content A company needs to translate a message for markets in Brazil, Spain, and France. They use `list_voices` to verify local accents (Portuguese, Spanish, French) before generating the video using `generate_video`. ## Benefits - Stop doing manual video editing. You simply hand off the script and let your agent handle voice selection and background music integration using `generate_video`. - Need multiple formats? Use one prompt to generate clips in different aspect ratios (16:9, 9:16, 1:1) for YouTube, TikTok, or Instagram stories instantly. - Worried about batch jobs failing? After calling `generate_video`, use `get_video` with the task ID. This lets you track status and download links in a systematic way. - Find the perfect voice every time. Before generating, run `list_voices`. You get access to all available accents and languages to match your target audience exactly. - Cut down on production time from days to minutes. Your agent acts as both the video editor and the studio director. ## How It Works The bottom line is: you define the content details once, and your agent manages the multi-step process of creation and retrieval. 1. First, use the `list_voices` tool to see what voices and languages are available. 2. Next, call the `generate_video` tool, providing your script along with specific parameters like voice name, aspect ratio, and background music preference. 3. Finally, wait a short time, then run `get_video` using the provided task ID to check if the video is ready. If it is, you get the direct download link. ## Frequently Asked Questions **How do I find out what voices are available using list_voices?** Run `list_voices` to get a full directory of all AI voices and their supported languages. This lets you pick the right accent (like American English) before generating. **What is the difference between generate_video and get_video?** `generate_video` starts the task, sending your script to the system for rendering. `get_video` checks on that specific job ID to see if it's finished or still processing. **Can generate_video handle different platforms like TikTok?** Yes. When calling `generate_video`, you specify the aspect ratio (like 9:16) so the video is perfectly formatted for that platform right out of the gate. **Is there a way to change the voice after I call generate_video?** No. You must select the desired voice and language parameters before running `generate_video`. Changes require starting a completely new generation task. **What do I need to do if my call to generate_video fails?** If the generation fails, it will return an explicit error code. Check the full response body for details. Common issues include using unsupported aspect ratios or having a script that exceeds character limits. **Can I use get_video to check on tasks from yesterday?** Yes, the status tracking is persistent for all created tasks. You simply need the unique task ID and can query the link anytime to see if it's complete or still processing. **What are the guidelines regarding background music when I call generate_video?** You must provide a valid identifier for the desired background track. The tool accepts standard asset IDs; you can list available options and select one specific track to include in your video. **How do I handle rate limits when calling generate_video?** The MCP handles basic rate limiting, but for high volume use, monitor the API response headers. If you hit a limit, implement an exponential backoff strategy before retrying your generation calls. **How can I see which AI voices are available for my video?** Use the `list_voices` tool. It will return a full list of available AI voices along with their supported languages, helping you choose the right one for the `generate_video` action. **Can I track the progress of a video I just started generating?** Yes! After starting a generation, use the `get_video` tool with the unique video ID. It will tell you if the video is 'queued', 'processing', or 'completed'. **How do I specify the video format, like for Instagram Reels or YouTube?** When using `generate_video`, you can provide the `aspectRatio` parameter. Use '9:16' for Reels/TikTok, '16:9' for YouTube, or '1:1' for square posts.