How to Use the Speechnotes MCP in Pydantic AI

Q: How do I check if a transcription job is finished using Speechnotes and Pydantic AI?

Call gettranscriptionstatus with the job ID. The agent receives the status and uses Pydantic validation to confirm that the result structure matches exactly what your model expects.

Q: What is the best way to list supported languages with Speechnotes and Pydantic AI?

Run listsupportedlanguages. This tool retrieves all available language codes from Speechnotes. Your agent validates this returned array against your defined Python type hints.

Q: Does Speechnotes require webhooks to be signed when using Pydantic AI?

Yes, it does. You must use generatewebhooksignature. This tool doesn't just validate the signature; your agent also validates that the resulting payload conforms to your required data model.

Q: If I want to audit my usage with Speechnotes and Pydantic AI, what tools do I use?

Use getusagestatistics for consumption logs. For a historical view of actual jobs, run listtranscriptionhistory. Both outputs are validated against your expected schema.

Q: How can I get the final result format from Speechnotes using Pydantic AI?

First, call gettranscriptionexport to see what formats are available. Then, you use that information when processing results via your agent. The whole process is type-checked.

Ensure data correctness with Pydantic AI and Speechnotes.

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 Pydantic AI

Create your Vinkius account to connect Speechnotes to Pydantic 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Transcribe remote audio files

The `transcribe_audio_url` tool takes a remote URL, initiating the job on Speechnotes. It returns a job ID instantly, which is key because your agent doesn't wait for the transcription to finish. Later, you use `get_transcription_status`. This checks the current state of the job with Speechnotes. Since Pydantic AI focuses on correctness, it ensures this status response matches an expected data type.

Manage webhooks and delivery

Use `list_configured_webhooks` to see all active Speechnotes delivery endpoints before running anything. This helps your agent build reliable connections. When a webhook hits, run `generate_webhook_signature`. Your Pydantic AI setup validates the payload structure and verifies the signature simultaneously, catching bad data immediately.

Query job history and metadata

Want to know what was processed? Use `list_transcription_history` to get a list of past jobs. The agent validates that every field in this historical record adheres to your Pydantic schemas. Need to clean up old records? Run `remove_transcription_job`. This deletes the job ID from Speechnotes, and your framework confirms the deletion success with validated data.

Setup guide

Set up Speechnotes MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "speechnotes-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Speechnotes tools.",
)

result = await agent.run("List recent Speechnotes transactions")
print(result.output)

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 Pydantic AI

Call `get_transcription_status` with the job ID. The agent receives the status and uses Pydantic validation to confirm that the result structure matches exactly what your model expects.

Run `list_supported_languages`. This tool retrieves all available language codes from Speechnotes. Your agent validates this returned array against your defined Python type hints.

Yes, it does. You must use `generate_webhook_signature`. This tool doesn't just validate the signature; your agent also validates that the resulting payload conforms to your required data model.

Use `get_usage_statistics` for consumption logs. For a historical view of actual jobs, run `list_transcription_history`. Both outputs are validated against your expected schema.

First, call `get_transcription_export` to see what formats are available. Then, you use that information when processing results via your agent. The whole process is type-checked.

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