# Coqui TTS MCP for AI Agents AI Agent Connect > Coqui TTS MCP lets you turn text into high-quality spoken audio directly through your AI agent. It connects to your Coqui Speech Studio API to list available models and synthesize voices on the fly. No more jumping between tabs to generate audio files. ## Overview - **Category:** developer-tools - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_mTxT2sdkPwqJs70KzThY3INSs9q7xXUbt1OMt9EN/ai-agent-connect - **Tags:** text-to-speech, tts, coqui-ai, speech-synthesis, voice-generation ## Description Coqui TTS MCP lets you turn text into high-quality spoken audio directly through your AI agent. It connects to your Coqui Speech Studio API to list available models and synthesize voices on the fly. No more jumping between tabs to generate audio files. Imagine you're building a voice-enabled app or just need a quick voiceover for a video. Usually, that means jumping between a text editor, a web interface for a speech engine, and a file manager to grab the final audio. This Connector changes that by bringing the power of Coqui's speech synthesis directly into your AI client. Instead of handling complex API calls or navigating a clunky dashboard, you just tell your agent what you want it to say. It handles the heavy lifting of talking to your hosted or local Coqui instance, grabbing the right model, and getting the audio ready. It's a huge time saver for anyone who needs to hear their text out loud without the friction of manual file management. When you're browsing the Vinkius catalog for ways to give your agent a voice, this is the go-to for high-quality, open-source synthesis. You get to stay in your flow, whether you're debugging a script or prepping a content calendar, while the agent handles the audio production in the background. This setup is perfect for keeping your creative momentum high, as you can iterate on scripts and hear the results immediately without any extra steps. ## Tools ### list_models See every text-to-speech model currently active on your Coqui instance. It helps you pick the right voice for the job. ### synthesize_speech Convert a string of text into a spoken audio file. It returns the metadata you need to find and play the result. ## Prompt Examples **Prompt:** ``` What voices do I have available? ``` **Response:** ``` I've checked your Coqui setup. You currently have 3 models active: * **Standard English VITS** * **Multilingual XTTS v2** * **Fast-Response Model** Which one should I use for your project? ``` **Prompt:** ``` Read this: 'The weather today is perfect for a walk in the park.' ``` **Response:** ``` I'm generating that audio for you now... **Done!** You can find the audio metadata and the file details here: | File Name | Duration | Model Used | | :--- | :--- | :--- | | walk_in_park.wav | 4.2s | Standard English VITS | Let me know if you'd like to hear another version. ``` **Prompt:** ``` Which model is best for a Spanish voiceover? ``` **Response:** ``` Based on your Coqui setup, the **multilingual/multi-dataset/xtts_v2** model is your best bet for Spanish. Would you like me to synthesize a sample using that one? ``` ## Capabilities ### List available speech models See every text-to-speech model currently active on your Coqui instance. ### Turn text into spoken audio Convert a string of text into a spoken audio file instantly. ### Get audio metadata Retrieve technical details about your generated audio files. ### Connect to local or cloud endpoints Link your AI agent to your specific Coqui Speech Studio setup. ### Automate voiceover production Generate audio files in bulk through natural language commands. ## Use Cases ### Rapid Video Scripting A creator asks the agent to read the first three paragraphs of a script and gets the audio back immediately to check the pacing. ### App Prototyping A developer tells the agent to generate a greeting using the multilingual model to test a new UI flow for a voice-enabled app. ### Model Consistency Testing A researcher asks the agent to synthesize ten lines of text to compare model consistency across different voices. ### Dynamic Content Generation A developer uses the agent to generate unique audio responses for a customer service bot based on specific user inputs. ## Benefits - Use `synthesize_speech` to create audio files without leaving your chat window. This lets you stay focused on your primary task while the agent handles the heavy lifting of audio production. - Check your available models using `list_models` to ensure you're using the right voice. You can quickly switch between different styles and languages as your project evolves. - Get audio metadata immediately so you don't have to hunt for files in folders. This makes it much easier to organize your assets during a busy production day. - Keep your data private by connecting to your own local Coqui instance. You maintain full control over your models and your data without relying on third-party cloud providers. - Batch generate voiceovers for content calendars by letting your agent handle the requests. Turn a long list of dialogue into a series of audio files in one go. ## How It Works The bottom line is you get a direct line from your chat interface to your custom voice synthesis engine. 1. Enter your Coqui Speech Studio URL into the Connector configuration. 2. Ask your agent to find your models or create a voiceover from text. 3. Get the audio metadata and your synthesized speech instantly. ## Frequently Asked Questions **Does the Coqui TTS MCP provide the voices?** No, this Connector connects to your own Coqui instance. You need to have your models hosted locally or in the cloud for the agent to access them. **Can I use this for real-time speech?** This is best for generating high-quality audio files and metadata. It's designed for workflows where you need to create specific voiceovers from text. **Do I need to host my own Coqui instance?** Yes, you need a Coqui Speech Studio API URL. This Connector acts as a bridge between your AI agent and your existing synthesis setup. **What kind of models can I use?** You can use any models that your Coqui instance supports, including various open-source models for different languages and styles. **Can I use this in Cursor or Claude?** Yes, this works with any MCP-compatible client, including Claude, Cursor, and Windsurf, allowing you to generate audio from your favorite editor. **Is there a limit on how much text I can synthesize?** The limits are determined by your own Coqui instance. You can generate anything from single sentences to longer script segments. **How can I check which voice models are currently installed on my server?** You can use the `list_models` tool. Your agent will query the Coqui server and return a list of all available TTS models ready for synthesis. **Is it possible to generate audio files from a text string directly?** Yes! Use the `synthesize_speech` tool by providing the text you want to convert. The agent will process it through Coqui and return the audio metadata. **What do I need to provide to connect my local Coqui instance?** You only need to provide the `COQUI_SERVER_URL`. This is the base address where your Coqui Speech Studio API is reachable (e.g., http://localhost:5002).