How to Use the Volcengine Speech Synthesis MCP in Mastra AI

Q: What is the best way to manage multi-language TTS tasks using Volcengine Speech Synthesis with Mastra AI?

The synthesizespeech tool natively handles multiple languages, letting you define the target language and style in a single call. This makes it easy for your agent to switch between generating English instructions and Chinese confirmations.

Q: If I need to adjust pacing or emphasis using Volcengine Speech Synthesis with Mastra AI, what tool should I use?

You'll need synthesizessml. This tool accepts SSML tags like and , giving your agent explicit control over the timing and intonation of every word generated.

Q: How does Mastra AI handle the status checking for a long-running audio task?

After triggering synthesis, you use gettaskstatus to poll the job. Your agent can check this repeatedly until the state reports 'completed,' ensuring your workflow doesn't stall waiting for background processing.

Q: Can I list all available voices before triggering a task with Volcengine Speech Synthesis and Mastra AI?

Yes, always start by using listvoices. This tool gives you an exhaustive catalog of every model, including the trendy or news styles, so your agent can choose the right fit for the job.

Build complex audio workflows with Mastra AI using Volcengine Speech Synthesis.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Volcengine Speech Synthesis MCP to Mastra AI

Create your Vinkius account to connect Volcengine Speech Synthesis to Mastra AI 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 Volcengine Speech Synthesis with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run advanced TTS processes via the MCP Server.

The `synthesize_speech` tool is your workhorse. It lets you define specific voice parameters—speed, volume, and style—while handling multiple languages (Chinese, English, Japanese). You can automatically trigger this synthesis step within a multi-step workflow. This means if one part of your business process fails, the next step can still attempt to generate necessary audio content for reporting or user notification.

Create proprietary voices using Volcengine Speech Synthesis.

You'll use `create_custom_voice` to train a unique brand voice. Just upload 10-50 high-quality audio samples, wait for the training period (1-3 days), and then reference that new `custom voice_type` in subsequent synthesis calls. Your agent can now generate consistent audio across all user interactions, making your application sound professional from start to finish.

Manage complex multi-part text generation.

If the content needs are extensive—think full documentation or an audiobook chapter—use `synthesize_long_text`. This tool handles texts over 1024 characters, preventing workflow breaks that happen with simple API calls. It ensures your agent can process and generate long-form audio assets without needing to break the content up manually.

Setup guide

Set up Volcengine Speech Synthesis MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Volcengine Speech Synthesis tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "volcengine-speech-synthesis-mcp-client",
  servers: {
    "volcengine-speech-synthesis-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Volcengine Speech Synthesis Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Volcengine Speech Synthesis tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Volcengine Speech Synthesis transactions"
);
console.log(result.text);

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 Volcengine Speech. 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 Volcengine Speech Synthesis 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 Volcengine Speech Synthesis MCP in Mastra AI

The `synthesize_speech` tool natively handles multiple languages, letting you define the target language and style in a single call. This makes it easy for your agent to switch between generating English instructions and Chinese confirmations.

You'll need `synthesize_ssml`. This tool accepts SSML tags like `` and ``, giving your agent explicit control over the timing and intonation of every word generated.

After triggering synthesis, you use `get_task_status` to poll the job. Your agent can check this repeatedly until the state reports 'completed,' ensuring your workflow doesn't stall waiting for background processing.

This server handles text content (for synthesis), raw audio recordings (for custom voice training), and generates output as binary audio data or URLs. Data is processed through the Volcengine Speech Synthesis MCP Server.

Yes, always start by using `list_voices`. This tool gives you an exhaustive catalog of every model, including the trendy or news styles, so your agent can choose the right fit for the job.

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