Can my agent transcribe an audio file from a public URL?

Yes. Use the 'transcribe_url' tool. Provide the public URL of the audio file (WAV, MP3, etc.) and specify the model (e.g., 'nova-2'). The agent will dispatch the request to Deepgram and return the transcribed text instantly.

How do I generate speech from text using the agent?

Use the 'speak_text' tool. Provide the text script and the target voice model (e.g., 'aura-asteria-en'). Your agent will trigger the high-fidelity Aura voice engine and return the binary audio stream data.

Can I monitor my remaining project balance via chat?

Absolutely. Use the 'get_balances' tool with your project ID. The agent will retrieve your current wallet thresholds and funding limits directly from Deepgram to ensure your audio pipelines stay active.

Deepgram MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Deepgram
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Deepgram through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Deepgram "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Deepgram?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Deepgram MCP Server

Connect your Deepgram account to any AI agent and take full control of your speech-to-text (STT) and text-to-speech (TTS) workflows through natural conversation.

Pydantic AI validates every Deepgram tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Speech-to-Text (STT) — Dispatch automated transcription requests for remote audio URLs using the lightning-fast Nova-2 model to consume explicit WAV/MP3 web streams
Text-to-Speech (TTS) — Generate high-fidelity audio from raw text using Aura voices, outputting the exact binary stream footprint natively from your chat
Usage Monitoring — Analyze specific global bounds hitting /usage to map literally terabytes of exact API transcription times and TTS byte usage
Project & Key Management — List and create ephemeral Deepgram access boundaries (API keys) and isolate organizational tenants where Audio AI billing is enforced
Wallet Oversight — Retrieve explicit cloud logging tracing explicit Vault limits and verify direct wallet thresholds to ensure pipelines never drop
Identity & Invites — Manage developer limits by listing members and sending team invites to specific project UUIDs strictly

The Deepgram MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Deepgram to Pydantic AI via MCP

Follow these steps to integrate the Deepgram MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Deepgram with type-safe schemas

Why Use Pydantic AI with the Deepgram MCP Server

Pydantic AI provides unique advantages when paired with Deepgram through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Deepgram integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Deepgram connection logic from agent behavior for testable, maintainable code

Deepgram + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Deepgram MCP Server delivers measurable value.

Type-safe data pipelines: query Deepgram with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Deepgram tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Deepgram and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Deepgram responses and write comprehensive agent tests

Deepgram MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Deepgram to Pydantic AI via MCP:

create_key

Identify precise active arrays spanning native Gateway auth

delete_key

Inspect deep internal arrays mitigating specific Plan Math

get_balances

Retrieve explicit Cloud logging tracing explicit Vault limits

get_usage

Perform structural extraction of properties driving active Account logic

list_keys

Provision a highly-available JSON Payload generating hard Customer bindings

list_members

Dispatch an automated validation check routing explicit Gateway history

list_projects

Identify bounded CRM records inside the Headless Deepgram Platform

send_invite

Identify precise active arrays spanning native Hold parsing

speak_text

Enumerate explicitly attached structured rules exporting active Billing

transcribe_url

Irreversibly vaporize explicit validations extracting rich Churn flags

Example Prompts for Deepgram in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Deepgram immediately.

"Transcribe this audio: https://example.com/recording.mp3 using nova-2"

"Generate speech for: 'The future of AI is agentic' using aura-asteria-en"

"Show me my Deepgram usage for this month"

Troubleshooting Deepgram MCP Server with Pydantic AI

Common issues when connecting Deepgram to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Deepgram + Pydantic AI FAQ

Common questions about integrating Deepgram MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Deepgram MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.