How to Use the Speechnotes MCP in Mastra AI

Q: How does Mastra AI handle job progress with Speechnotes?

You use gettranscriptionstatus within a workflow step. The agent will wait and check this status until the transcription job is confirmed as complete or failed.

Q: Can I list my past Speechnotes jobs using the Mastra AI framework?

Yes, call listtranscriptionhistory. This provides a clean audit trail that can be attached as evidence to your workflow's final output record.

Q: How do I confirm the connection to Speechnotes using the Mastra AI agent?

Run testspeechnotesauth as a preliminary step in your workflow. This verifies that credentials and network access are correct before committing to expensive transcription runs.

Speechnotes: Build complex, failure-proof workflows for the Mastra AI agent framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Speechnotes MCP to Mastra AI

Create your Vinkius account to connect Speechnotes to Mastra AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Speechnotes with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Build Failure-Proof Workflows with Speechnotes

Mastra AI needs reliability. Use `transcribe_audio_url` within a workflow that includes automatic retries if the initial API call fails due to transient network issues. The MCP Server handles the job execution, and your agent framework manages the failure recovery. If a transcription attempt fails, you can set up conditional logic using `get_usage_statistics` to check remaining credits before triggering an expensive retry loop.

Speechnotes MCP Server for State Management

The workflow engine requires knowing the current state of a job. Call `get_transcription_status` at key points in your sequence: after submission, before export, and during verification. This keeps the multi-step process from stalling. When the transcript is ready, use `get_transcription_export` to finalize the output format. The Mastra AI framework ensures this step only runs if the status check confirms completion.

Speechnotes Job Management for Complex Workflows

Complex workflows often need cleanup or verification steps. Use `list_transcription_history` to pull records needed for auditing, and use `remove_transcription_job` if the entire workflow must be aborted gracefully. This prevents orphaned jobs from consuming credits. The MCP Server's ability to list configured webhooks (`list_configured_webhooks`) helps you map out the full data flow dependencies in your process.

Setup guide

Set up Speechnotes 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 Speechnotes 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: "speechnotes-mcp-client",
  servers: {
    "speechnotes-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Speechnotes 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 Speechnotes. 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 Speechnotes 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 Speechnotes MCP in Mastra AI

You use `get_transcription_status` within a workflow step. The agent will wait and check this status until the transcription job is confirmed as complete or failed.

Mastra AI's built-in retry logic can manage failures. You can also check usage via `get_usage_statistics` to ensure retries are financially sound.

Yes, call `list_transcription_history`. This provides a clean audit trail that can be attached as evidence to your workflow's final output record.

The server handles raw audio URLs, job status updates, and resulting text transcripts. All these data points must be accounted for when designing your secure workflow.

Run `test_speechnotes_auth` as a preliminary step in your workflow. This verifies that credentials and network access are correct before committing to expensive transcription runs.

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