# Play.ht MCP for AI Agents AI Agent Connect

> Play.ht MCP lets you turn text into human-like speech. It gives your AI agent access to a huge library of neural voices, lets you pick specific formats like MP3 or WAV, and lets you check the status of long audio generation requests.

## Overview
- **Category:** productivity
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_zBhREyAH4d3fHuv74MXg2YbWldTOlGZliGtiSkZF/ai-agent-connect
- **Tags:** text-to-speech, ai-voices, speech-synthesis, voice-generation, neural-tts

## Description

Imagine you're building a tool that needs to talk back to people, or maybe you're a content creator who hates the time it takes to record voiceovers for every single video. This Connector changes that by letting your AI agent handle the heavy lifting of speech synthesis. Instead of jumping between tabs to find the right voice or manually uploading files, your agent can pull from Play.ht's library, pick a specific voice ID, and start the conversion process immediately. It handles the technical bits like quality levels and file formats while you just focus on the script. If you're looking for a way to put high-quality audio into your production pipeline, finding this in the Vinkius catalog makes it easy to plug into your current workflow without the usual friction of manual API management. It's about getting that final audio file without the headache of managing the synthesis steps yourself.

## Tools

### get_tts_status
Checks if a long-running audio generation request is finished or still processing. Use this to monitor large files.

### get_voices
Lists all the available voices in the Play.ht library so you can find the right one. It shows IDs and metadata.

### convert_tts
Converts your text into a speech file with specific voice and quality settings. This is the primary tool for creating audio assets.

## Prompt Examples

**Prompt:** 
```
Find a professional-sounding male voice for a tech podcast.
```

**Response:** 
```
I've looked through the Play.ht library. Here are a few options that fit a tech podcast style:

| Voice Name | Gender | Style |
| :--- | :--- | :--- |
| **Larry** | Male | Professional & Clear |
| **William** | Male | Deep & Authoritative |
| **James** | Male | Friendly & Tech-savvy |

Would you like to use one of these for your script?
```

**Prompt:** 
```
Convert 'Hello world' to a high-quality MP3 using the 'Larry' voice.
```

**Response:** 
```
I've started that conversion for you using the 'Larry' voice at high quality. 

**Request Details:**
- **Status:** Processing
- **Transcription ID:** `trans_88291` 

I'll keep an eye on this and let you know as soon as the MP3 is ready.
```

**Prompt:** 
```
Is my audio file ready yet? The ID is 'trans_88291'.
```

**Response:** 
```
Good news! The conversion for `trans_88291` is complete. 

**File Details:**
- **Status:** Finished
- **Format:** MP3
- **Download Link:** [Click here to download your audio](https://play.ht/example-link)
```

## Capabilities

### Browse the voice library
Let your agent see every available voice, including language and gender metadata.

### Convert text to speech
Turn your written content into high-quality audio files instantly.

### Track audio generation
Check the progress of long-running transcription requests using a unique ID.

### Select audio formats
Choose between MP3 or WAV files and set the quality from draft to high.

## Use Cases

### Batch narrating product descriptions
A creator asks the agent to generate audio for 50 products using a specific male voice to save hours of manual recording.

### Adding human-like voices to an app
A developer uses convert_tts to give their custom application a realistic voice instead of a robotic system default.

### Monitoring large audio renders
An agent uses get_tts_status to poll for a finished file while the user continues working on other tasks.

### Finding a specific brand voice
The user asks the agent to find a calm female voice in a specific language using get_voices to find the right ID.

## Benefits

- Stop hunting for voices manually because get_voices lets your agent browse the library for you.
- Get high-quality audio files in MP3 or WAV formats directly through convert_tts without extra steps.
- Stay updated on long audio tasks using get_tts_status to know exactly when a file is ready.
- Save time on video production by having your agent batch-process narrations using specific voice IDs.
- Ensure consistency across projects by letting your agent stick to specific neural voices for every request.

## How It Works

The bottom line is your agent handles the entire speech synthesis lifecycle from voice selection to final file delivery.

1. Connect your Play.ht API key and User ID to the Connector.
2. Tell your agent which text to convert and which voice to use.
3. Get the final audio URL once the status check confirms it's done.

## Frequently Asked Questions

**Can Play.ht MCP generate voices for different languages?**
Yes, it gives your agent access to a wide variety of voices across many different languages and accents.

**What file formats can I get with Play.ht MCP?**
You can choose between standard MP3 and high-fidelity WAV formats depending on your project needs.

**How does it handle long audio files?**
The Connector includes a status tracking tool that lets your agent check on long-running requests so you don't have to guess when they're done.

**Can I choose the quality of the voice?**
Yes, you can specify the quality level from Draft to High to balance speed and audio fidelity.

**Does it work with my current AI client?**
It works with any MCP-compatible client, including Claude, Cursor, and Windsurf.

**How do I get my API keys for Play.ht?**
You can find your API key and User ID in your Play.ht account dashboard settings.

**How can I find the right voice ID for my language?**
Use the `get_voices` tool. It returns a complete list of available voices, allowing you to filter by name, language, and gender to find the perfect match for your project.

**Can I control the speed and format of the generated audio?**
Yes! When using `convert_tts`, you can specify the `speed` (from 0.5 to 2.0), the `output_format` (like mp3 or wav), and the `quality` level to suit your needs.

**What should I do if a conversion takes a long time?**
For longer texts, use the `get_tts_status` tool with your `transcription_id`. This allows you to check if the audio is still processing or ready for download.