# Play.ht MCP for AI Agents AI Agent Connect

> Play.ht (Voice Cloning) lets you generate ultra-realistic speech and create instant voice clones using Play.ht's voice engines directly from your agent. It handles everything from converting text to audio to mimicking specific voices based on short samples.

## Overview
- **Category:** ai-frontier
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_GOWw2EkNfCcipiaxRhjhVT8OcQmHdgozyQknlJBZ/ai-agent-connect
- **Tags:** text-to-speech, voice-cloning, tts, audio-generation, synthetic-media, speech-synthesis

## Description

Play.ht gives your AI agent the ability to generate high-quality Text-to-Speech and create instant voice clones through natural conversation. You can convert text into lifelike audio using various engines like Play3.0-mini and PlayHT2.0-turbo. If you need a specific voice for a project, you can create a digital twin of any voice by providing a short audio sample. This Connector gives you fine-grained control over the output, letting you adjust speed, quality, emotion, and temperature to get the exact vocal performance you need. It also handles multi-language support, so you can generate speech in English, French, Spanish, and more. When you find this in the Vinkius catalog, you're getting a tool to automate voiceovers for videos and podcasts, integrate realistic voices into games, or create personalized localized content at scale. Instead of spending hours in a recording studio or hiring a voice actor for every single line of dialogue, you can just describe the tone you want to your agent. It handles the technical side of the synthesis, turning your scripts into production-ready audio files in seconds. This is a major shift for anyone who needs to produce high-quality audio content quickly and consistently. Whether you are building a game with unique characters or a marketing campaign that needs to reach different countries, this tool handles the heavy lifting of voice generation so you can focus on the creative side of your work.

## Tools

### generate_tts_stream
Convert text into high-quality audio using Play.ht's advanced speech engines. You can specify emotions and speeds to get the exact delivery you need.

### create_instant_voice_clone
Create a digital twin of a specific voice by providing a base64 encoded audio sample. This lets you build a custom voice library for your projects.

## Prompt Examples

**Prompt:** 
```
Make a 30-second audio clip of a narrator saying 'Welcome to our new podcast' with a deep, warm tone.
```

**Response:** 
```
| **Audio Generation Request** |
| :--- | :--- |
| **Script** | "Welcome to our new podcast" |
| **Voice Style** | Deep, Warm Narrator |
| **Status** | Processing... |

I'm generating that for you now. You'll get an audio file with a warm, professional tone suitable for a podcast intro.
```

**Prompt:** 
```
I have a recording of my friend. Can you make a voice clone of him for my game?
```

**Response:** 
```
| **Voice Cloning Request** |
| :--- | :--- |
| **Source** | Provided Audio Sample |
| **Clone Name** | "Game Character" |
| **Status** | Uploading... |

I'm uploading your friend's sample now. Once it's done, I'll provide you with a unique Voice ID you can use to generate any dialogue for your character.
```

**Prompt:** 
```
Translate this text to Spanish and make it sound like an excited commercial.
```

**Response:** 
```
| **Localized Audio Request** |
| :--- | :--- |
| **Language** | Spanish |
| **Emotion** | Excited |
| **Status** | Synthesizing... |

I'm converting your script into a high-energy Spanish commercial. I'll use the excited emotion tag to ensure it sounds like a professional advertisement.
```

## Capabilities

### Create digital voice twins
Generate a unique voice clone from a short audio sample.

### Turn text into lifelike audio
Convert written scripts into high-quality speech using various engines.

### Adjust vocal emotion and speed
Fine-tune the delivery to match a specific mood or pace.

### Produce multi-language speech
Generate natural-sounding audio in several different languages.

### Generate audio streams
Get high-quality audio output directly for your applications.

## Use Cases

### Automating Podcast Intros
A creator asks the agent to turn a weekly script into a voiceover using a cloned host voice.

### Localized Video Ads
A marketer needs to turn a Spanish script into audio that matches the tone of their English brand voice.

### Dynamic Game NPCs
A dev wants the agent to generate unique dialogue for a character based on a specific personality sample.

### Rapid Prototype Audio
A startup wants to hear how a product description sounds in three different languages before recording.

## Benefits

- Skip the recording studio by using create_instant_voice_clone to build a library of custom voices from small samples.
- Get precise control over your audio output by adjusting speed and emotion settings within generate_tts_stream.
- Scale your content production without hiring voice actors by automating your entire voiceover workflow.
- Reach global audiences faster by generating multi-language speech that sounds natural in different regions.
- Reduce production costs for games and apps by creating unique, consistent voices for every character.

## How It Works

The bottom line is you get production-ready voice clones and speech without the manual recording process.

1. Connect your Play.ht account by providing your User ID and API Key.
2. Upload a base64 audio sample or provide text for generation.
3. Receive a Voice ID or a direct audio stream for your project.

## Frequently Asked Questions

**How can I use Play.ht (Voice Cloning) to create a custom voice?**
You can create a custom voice by providing a short audio sample of the person you want to clone. The Connector will then generate a unique Voice ID that you can use for any text-to-speech task.

**Does Play.ht (Voice Cloning) support multiple languages?**
Yes, it supports several languages including English, French, and Spanish. This allows you to generate localized content while maintaining a consistent vocal identity.

**Can I change the emotion of the speech with Play.ht (Voice Cloning)?**
Yes, you can specify different emotions like 'happy' or 'excited' during the generation process. This ensures the audio matches the specific mood of your content.

**What kind of audio samples do I need for Play.ht (Voice Cloning)?**
You just need a short, clear audio sample of the target voice. The Connector handles the processing to create a digital twin from that recording.

**Can I use Play.ht (Voice Cloning) for my YouTube videos?**
It's perfect for YouTube. You can automate your voiceovers, create consistent narrations for your series, and skip the need for manual recording every time you upload.

**Is Play.ht (Voice Cloning) good for game development?**
Yes, it's great for creating unique voices for NPCs. You can clone specific voices to give your characters distinct identities without recording every line of dialogue.

**How can I generate audio from text using a specific voice?**
Use the `generate_tts_stream` tool. Provide the text and the unique voice ID. You can also customize the `voice_engine` (like Play3.0-mini) and `emotion` for better results.

**Can I create a new voice clone with this server?**
Yes! Use the `create_instant_voice_clone` tool. You'll need to provide a name for the voice and a base64 encoded audio sample of the voice you want to clone.

**What audio formats are supported for generation?**
When using `generate_tts_stream`, you can specify the `output_format` as mp3, wav, ogg, flac, or mulaw.