Bring Speech To Text
to CrewAI
Learn how to connect Deepgram to CrewAI 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 CrewAI?
When paired with CrewAI, Deepgram becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Deepgram tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.
- —
Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools
- —
CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the
mcpsparameter and agents auto-discover every available tool at runtime - —
Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls
- —
Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports
Deepgram in CrewAI
Deepgram and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Deepgram to CrewAI 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 CrewAI
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 CrewAI 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 CrewAI
Every tool call from CrewAI 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 CrewAI discover and connect to MCP tools?
CrewAI connects to MCP servers lazily. when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.
Can different agents in the same crew use different MCP servers?
Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.
What happens when an MCP tool call fails during a crew run?
CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.
Can CrewAI agents call multiple MCP tools in parallel?
CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.
Can I run CrewAI crews on a schedule (cron)?
Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.
MCP tools not discovered
Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts. check console output.
Agent not using tools
Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".
Timeout errors
CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.
Rate limiting or 429 errors
Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.