How to Use the Lovo AI (Genny TTS & Voice Synthesis API) MCP in Vercel AI SDK

Q: How do I initialize the Lovo AI (Genny TTS & Voice Synthesis API) with the Vercel AI SDK?

Install @ai-sdk/mcp and set up your MCP endpoint. Use createMCPClient to connect to this server, then pass mcpClient.tools() directly to generateText or streamText to let your agent call the voice tools.

Q: How does the Vercel AI SDK handle voice selection with the Lovo AI (Genny TTS & Voice Synthesis API)?

Your agent calls listvoices to retrieve the available speaker profiles. It can then inspect details via getspeaker to programmatically select the voice ID that best matches your user's preferences before starting the synthesis.

Generate and play synthetic voices directly inside your Next.js application using the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lovo AI (Genny TTS & Voice Synthesis API) MCP to Vercel AI SDK

Create your Vinkius account to connect Lovo AI (Genny TTS & Voice Synthesis API) to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Lovo AI (Genny TTS & Voice Synthesis API) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Dynamic Voice Generation in Next.js Apps

Your frontend shouldn't wait around for heavy audio processing. When you trigger `create_tts_job`, your Vercel AI SDK client fires the generation job and handles the response without blocking the main browser thread. The client then monitors the job status by polling `get_tts_job` in the background. Once the audio file is ready, the URL is fed directly into your React state so your users can play the speech instantly.

Real-time Voice Discovery for UI Customization

Let your users choose their own narrator on the fly. This MCP Server lets your agent call `list_voices` to fetch the complete directory of Lovo speakers directly inside your Edge Functions. You can instantly render a dropdown of voice options or let your agent pick the best fit. By calling `get_speaker`, the agent inspects specific voice styles and profiles to match the user's current mood.

Zero-Lag Audio Pipelines with Vercel AI SDK

Building voice apps on the edge means you need to avoid heavy cold starts. This MCP Server bypasses heavy local dependencies by offloading the entire synthesis pipeline to external API endpoints. Your agent coordinates the lifecycle of each track from `create_tts_job` to final playback. This keeps your bundle sizes small and your application fast enough to run on Vercel's global edge network.

Setup guide

Set up Lovo AI (Genny TTS & Voice Synthesis API) MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Lovo AI (Genny TTS & Voice Synthesis API) tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Lovo AI (Genny TTS & Voice Synthesis API) transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Lovo AI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Lovo AI (Genny TTS & Voice Synthesis API) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Lovo AI (Genny TTS & Voice Synthesis API) MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and set up your MCP endpoint. Use `createMCPClient` to connect to this server, then pass `mcpClient.tools()` directly to `generateText` or `streamText` to let your agent call the voice tools.

The Lovo AI (Genny TTS & Voice Synthesis API) operates as an asynchronous job queue. Your agent triggers `create_tts_job` and polls `get_tts_job` to get the final audio URL, which you can then stream directly into your standard HTML5 audio player.

Your agent calls `list_voices` to retrieve the available speaker profiles. It can then inspect details via `get_speaker` to programmatically select the voice ID that best matches your user's preferences before starting the synthesis.

No. The credentials for this MCP Server are managed entirely on Vinkius. Your Vercel AI SDK client only needs to authenticate with your single Vinkius endpoint token, keeping your secret keys hidden.

This server only processes the raw text strings you send for synthesis and the resulting audio file URLs. Vinkius runs the server in an isolated sandbox, meaning your input text is never saved or cached locally after the API request is completed.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript