Compatible with every major AI agent and IDE
What is the Play.ht (Voice Cloning) MCP Server?
Connect Play.ht to your AI agent to generate high-quality Text-to-Speech (TTS) and create instant voice clones through natural conversation.
What you can do
- Text-to-Speech Generation — Convert text into lifelike audio using various engines like Play3.0-mini and PlayHT2.0-turbo.
- Instant Voice Cloning — Create a digital twin of any voice by simply providing a short audio sample.
- Fine-grained Control — Adjust speed, quality, emotion, and temperature to get the perfect vocal performance.
- Multi-language Support — Generate speech in multiple languages including English, French, Spanish, and more.
How it works
- Subscribe to this server
- Enter your Play.ht User ID and API Key
- Start generating audio and cloning voices from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Content Creators — automate voiceovers for videos and podcasts without manual recording
- Developers — integrate realistic voice interactions into applications and games
- Marketers — create personalized audio messages and localized content at scale
Built-in capabilities (2)
Provide the audio file as a base64 encoded string. Create an instant voice clone from an audio sample
Generate audio from text using Play.ht TTS
Why LlamaIndex?
LlamaIndex agents combine Play.ht (Voice Cloning) tool responses with indexed documents for comprehensive, grounded answers. Connect 2 tools through Vinkius and query live data alongside vector stores and SQL databases in a single turn. ideal for hybrid search, data enrichment, and analytical workflows.
- —
Data-first architecture: LlamaIndex agents combine Play.ht (Voice Cloning) tool responses with indexed documents for comprehensive, grounded answers
- —
Query pipeline framework lets you chain Play.ht (Voice Cloning) tool calls with transformations, filters, and re-rankers in a typed pipeline
- —
Multi-source reasoning: agents can query Play.ht (Voice Cloning), a vector store, and a SQL database in a single turn and synthesize results
- —
Observability integrations show exactly what Play.ht (Voice Cloning) tools were called, what data was returned, and how it influenced the final answer
Play.ht (Voice Cloning) in LlamaIndex
Play.ht (Voice Cloning) and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Play.ht (Voice Cloning) to LlamaIndex through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Play.ht (Voice Cloning) in LlamaIndex
The Play.ht (Voice Cloning) MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 2 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in LlamaIndex only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Play.ht (Voice Cloning) for LlamaIndex
Every tool call from LlamaIndex to the Play.ht (Voice Cloning) MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
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.
How does LlamaIndex connect to MCP servers?
Use the MCP client adapter to create a connection. LlamaIndex discovers all tools and wraps them as query engine tools compatible with any LlamaIndex agent.
Can I combine MCP tools with vector stores?
Yes. LlamaIndex agents can query Play.ht (Voice Cloning) tools and vector store indexes in the same turn, combining real-time and embedded data for grounded responses.
Does LlamaIndex support async MCP calls?
Yes. LlamaIndex's async agent framework supports concurrent MCP tool calls for high-throughput data processing pipelines.
BasicMCPClient not found
Install: pip install llama-index-tools-mcp
Explore More MCP Servers
View all →
Gerrit
10 toolsManage code reviews via Gerrit — query changes and patch sets, handle reviewers and approvals, and audit project branches directly from any AI agent.

LegiScan Legislation Lookup
3 toolsUniversal legislative intelligence — search bills, votes, and state laws via AI.

Dastra
12 toolsStay GDPR compliant with privacy management tools for data mapping, consent records, and breach notification workflows.

Honeywell Home
10 toolsConnect Honeywell Home to any AI agent via MCP.
