Bring Speech To Text
to Pydantic AI
Learn how to connect Deepgram to Pydantic AI and start using 6 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the 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.
What you can do
- Transcription Orchestration — Convert speech from public audio or video URLs into high-fidelity text programmatically using the latest Nova-3 models with smart formatting and diarization
- Neural Speech Synthesis — Programmatically generate natural-sounding audio from text input using the high-speed Aura engine to coordinate voice-enabled interfaces
- Model Discovery — Access complete directories of high-performance STT and TTS models supported by Deepgram to ensure the perfect accuracy and latency for your content
- Project & Usage Monitoring — Programmatically track your API utilization, minute consumption, and request counts across multiple projects for instant operational reporting
- Credential Lifecycle — Retrieve identifiers for active API keys associated with your projects directly through your agent to maintain high-fidelity security oversight
How it works
1. Subscribe to this server
2. Retrieve your API Key from the Deepgram Console
3. Start transcribing and synthesizing audio from Claude, Cursor, or any MCP client
No more manual file uploading or complex latency tuning in the portal. Your AI acts as your dedicated audio engineer and media production coordinator.
Who is this for?
- Developers & Engineers — instantly transcribe recorded meetings and integrate high-speed TTS into applications using natural language commands
- Content Creators — automate the generation of voiceovers and subtitles for global video assets without leaving your workspace
- Research Teams — scale the processing of interview recordings and monitor usage limits through simple AI queries
Built-in capabilities (6)
Generate audio from text (TTS)
Check API usage and limits
List active API keys
List high-performance AI models
List your Deepgram projects
Transcribe an audio file via URL
Why Pydantic AI?
Pydantic AI validates every Deepgram tool response against typed schemas, catching data inconsistencies at build time. Connect 6 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.
- —
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 in Pydantic AI
Deepgram and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Deepgram to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Deepgram in Pydantic AI
The Deepgram 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. All 6 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* 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
How Vinkius secures
Deepgram for Pydantic AI
Every tool call from Pydantic AI to the Deepgram MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I get a Deepgram API Key?
Log in to the Deepgram Console, navigate to the API Keys section, and create a new key with the necessary permissions.
What is the Nova-3 model?
Nova-3 is Deepgram's latest state-of-the-art transcription model, offering unmatched speed and accuracy for real-world audio.
Can I synthesize speech in different voices?
Yes! The convert_text_to_speech tool allows you to specify models like aura-asteria-en or aura-orion-en for different vocal profiles.
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.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai