How to Use the Speechnotes MCP in Claude Code

Q: How do I check if the Speechnotes MCP Server works with Claude Code?

Run the testspeechnotesauth command line tool. It’s a quick, non-GUI verification that tells you immediately if your connection is valid for scripting.

Q: What are the available Speechnotes models I can access with Claude Code?

You call listtranscriptionmodels to get a list of all engine versions. This lets you test different accuracy levels in your scripts.

Q: How do I check my Speechnotes usage logs using Claude Code?

Execute the getusagestatistics command. It outputs detailed resource consumption data, which is perfect for logging into a monitoring system.

Q: Can I list past jobs from Speechnotes when running scripts with Claude Code?

Yes. Use listtranscriptionhistory to pull records of every completed job directly in your terminal session for auditing purposes.

Speechnotes for Claude Code: Run reliable, headless audio transcriptions and manage jobs entirely via shell scripting or CI/CD pipelines.

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 Claude Code

Create your Vinkius account to connect Speechnotes to Claude Code — 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Batch Transcribe Remote Files

When running a script in a GitHub Action, you don't have time for manual steps. Use `transcribe_audio_url` to process remote files directly from the terminal. This makes it ideal for CI/CD pipelines where you need consistent results without GUI intervention.

Monitor Job Status Headlessly

A script needs confirmation. You can check job progress using `get_transcription_status` in a loop. This ensures your pipeline doesn't fail just because it waited too long. It’s essential for robust, unattended server-side execution.

Manage Webhook Endpoints

You need to tell the system where to send data. Use `list_configured_webhooks` to confirm your delivery endpoints are set up correctly in your script. Keep an eye on security using `generate_webhook_signature` when building webhook validation into your shell scripts.

Setup guide

Set up Speechnotes MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see speechnotes-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Speechnotes transactions." It will automatically discover and invoke the available Speechnotes tools.

Terminal

claude mcp add --transport http speechnotes-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Speechnotes MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "speechnotes-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Code

Run the `test_speechnotes_auth` command line tool. It’s a quick, non-GUI verification that tells you immediately if your connection is valid for scripting.

You call `list_transcription_models` to get a list of all engine versions. This lets you test different accuracy levels in your scripts.

Execute the `get_usage_statistics` command. It outputs detailed resource consumption data, which is perfect for logging into a monitoring system.

Yes. Use `list_transcription_history` to pull records of every completed job directly in your terminal session for auditing purposes.

This server touches audio upload data and associated transcription results. It's critical that you handle this information according to standard security protocols.

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