SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Rev AI MCP with Pydantic AI

Connect Pydantic AI to Rev AI MCP. Transcribe uploaded "team_meeting.mp3" audio file, get caption file for latest transcript, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Rev AI logoRev AI
Api Key

Rev AI is a speech-to-text platform offering high-quality transcripts, captions, and subtitles. It's known for combining human expertise with AI for accurate, affordable results.

36 Tools

Introduction

This guide walks you through connecting Rev AI to Pydantic AI using the Composio tool router. By the end, you'll have a working Rev AI agent that can transcribe uploaded "team_meeting.mp3" audio file, get caption file for latest transcript, check status of transcript for order 12345 through natural language commands.

This guide will help you understand how to give your Pydantic AI agent real control over a Rev AI account through Composio's Rev AI MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Rev AI with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIAutoGen

TL;DR

Here's what you'll learn:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Rev AI
  • How to attach an MCP Server to a Pydantic AI agent
  • How to stream responses and maintain chat history
  • How to build a simple REPL-style chat interface to test your Rev AI workflows

What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.

Key features include:

  • Type Safety: Built on Pydantic for automatic data validation
  • MCP Support: Native support for Model Context Protocol servers
  • Streaming: Built-in support for streaming responses
  • Async First: Designed for async/await patterns

What is the Rev AI MCP server, and what's possible with it?

The Rev AI MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Rev AI account. It provides structured and secure access to your transcription and speech analysis workflows, so your agent can transcribe recordings, generate captions, translate transcripts, identify languages, and analyze topics and sentiment on your behalf.

  • Audio and video transcription: Have your agent submit recorded media for transcription, check its progress, retrieve completed transcripts, and generate concise summaries.
  • Captions and translations: Let the agent retrieve captions in SRT or VTT format and fetch translated captions or transcripts for completed recordings.
  • Live transcription: Direct your agent to create live RTMP sessions or start WebSocket streams for real-time transcription of audio and video.
  • Language and speech alignment: Instruct your agent to identify the language spoken in a recording or align existing transcript text with its source audio.
  • Topic and sentiment analysis: Have your agent analyze text or transcripts to identify key themes and detect positive, negative, or neutral sentiment.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account with an active API key
  • Basic familiarity with Python and async programming
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

bash
pip install composio pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Rev AI
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your agent to Composio's API
  • USER_ID associates your session with your account for secure tool access
  • OPENAI_API_KEY to access OpenAI LLMs
5

Import dependencies

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
What's happening:
  • We load environment variables and import required modules
  • Composio manages connections to Rev AI
  • MCPServerStreamableHTTP connects to the Rev AI MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant
6

Create a Tool Router Session

python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Rev AI
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["rev"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
What's happening:
  • We're creating a Tool Router session that gives your agent access to Rev AI tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
7

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
rev_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[rev_mcp],
    instructions=(
        "You are a Rev AI assistant. Use Rev AI tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Rev AI endpoint
  • The agent uses GPT-5 to interpret user commands and perform Rev AI operations
  • The instructions field defines the agent's role and behavior
8

Build the chat interface

python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Rev AI.\n")

while True:
    user_input = input("You: ").strip()
    if user_input.lower() in {"exit", "quit", "bye"}:
        print("\nGoodbye!")
        break
    if not user_input:
        continue

    print("\nAgent is thinking...\n", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
What's happening:
  • The agent reads input from the terminal and streams its response
  • Rev AI API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns
9

Run the application

python
if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • The asyncio loop launches the agent and keeps it running until you exit

Complete Code

Here's the complete code to get you started with Rev AI and Pydantic AI:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Rev AI
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["rev"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    rev_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[rev_mcp],
        instructions=(
            "You are a Rev AI assistant. Use Rev AI tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Rev AI.\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "bye"}:
            print("\nGoodbye!")
            break
        if not user_input:
            continue

        print("\nAgent is thinking...\n", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You've built a Pydantic AI agent that can interact with Rev AI through Composio's Tool Router. With this setup, your agent can perform real Rev AI actions through natural language. You can extend this further by:
  • Adding other toolkits like Gmail, HubSpot, or Salesforce
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Rev AI for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.
TOOLS

Supported Tools

Every Rev AI action and event your agent gets out of the box.

Create RTMP Stream

Tool to create an RTMP live stream session for real-time transcription of live audio/video streams.

Delete Alignment Job

Tool to delete a forced alignment job and its associated data.

Delete Custom Vocabulary

Tool to delete a completed custom vocabulary and its data.

Delete Job By ID

Tool to delete a completed transcription job and its data.

Delete Language ID Job

Tool to delete a language identification job and its associated data.

Delete Sentiment Analysis Job

Tool to delete a specific sentiment analysis job and its associated data.

Delete Topic Extraction Job

Tool to delete a topic extraction job and its associated data.

Get Account

Retrieves Rev AI account information including email, credit balance (in hours), and HIPAA status.

Get Alignment Job

Tool to get details of a specific forced alignment job including its status.

Get Alignment Transcript

Tool to retrieve the aligned transcript with timestamps for a completed alignment job.

Get Captions

Tool to retrieve captions (SRT or VTT) for a completed Rev.

Get Captions Translation

Tool to retrieve translated captions for a completed Rev.

Get Custom Vocabulary Details

Tool to retrieve custom vocabulary processing details.

Get Job by ID

Tool to fetch details of a transcription job by its ID.

Get Language ID Job

Tool to fetch details of a language identification job by its ID.

Get Language Identification Result

Tool to retrieve language identification results for a completed job.

Get List of Jobs

Retrieves a list of transcription jobs from the past 30 days in reverse chronological order (newest first).

Get Sentiment Job

Tool to fetch details of a sentiment analysis job by its ID.

Get Sentiment Analysis Result

Tool to retrieve sentiment analysis results for a completed Rev.

Get Topic Extraction Result

Tool to retrieve topic extraction results for a completed job.

Get Topic Job

Tool to fetch details of a topic extraction job by its ID.

Get Transcript by ID

Tool to retrieve the transcript of a completed Rev.

Get Transcript Summary

Tool to retrieve a summary of the transcript for a completed transcription job.

Get Transcript Translation

Tool to retrieve a translated version of the transcript for a completed Rev.

List Alignment Jobs

Tool to retrieve a list of all forced alignment jobs for the account.

List Custom Vocabularies

Tool to retrieve a list of all custom vocabularies for the account.

List Language Identification Jobs

Tool to retrieve a list of language identification jobs for the account.

List Sentiment Analysis Jobs

Tool to retrieve a list of all sentiment analysis jobs for the account.

List Topic Extraction Jobs

Tool to retrieve a list of all topic extraction jobs for the account.

Start Stream Transcription

Tool to start a WebSocket transcription stream.

Submit Alignment Job

Tool to submit an audio file with existing transcript for forced alignment.

Submit Custom Vocabulary

Submits a custom vocabulary to Rev.

Submit Language ID Job

Tool to submit an audio file for language identification to detect the spoken language.

Submit Sentiment Analysis Job

Submit text for sentiment analysis to detect positive, negative, or neutral sentiments.

Submit Topic Extraction Job

Tool to submit text or transcripts for topic extraction to identify key topics and themes.

Submit Transcription Job

Submit an audio or video file for asynchronous transcription using Rev.

FRAMEWORKS

How to build Rev AI MCP Agent with another framework

Claude Code logo

Claude Code

Use Rev AI MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Rev AI MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Rev AI MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Rev AI MCP with Claude Agent SDK

Codex logo

Codex

Use Rev AI MCP with Codex

OpenClaw logo

OpenClaw

Use Rev AI MCP with OpenClaw

Hermes logo

Hermes

Use Rev AI MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Rev AI MCP with Atomic Agent

Google ADK logo

Google ADK

Use Rev AI MCP with Google ADK

LangChain logo

LangChain

Use Rev AI MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Rev AI MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Rev AI MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Rev AI MCP with LlamaIndex

CrewAI logo

CrewAI

Use Rev AI MCP with CrewAI

AutoGen logo

AutoGen

Use Rev AI MCP with AutoGen

FAQ

Frequently asked questions

With a standalone Rev AI MCP server, the agents and LLMs can only access a fixed set of Rev AI tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Rev AI and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Pydantic AI fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Rev AI tools.

Yes, absolutely. You can configure which Rev AI scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Rev AI data and credentials are handled as safely as possible.

Start with Rev AI.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Rev AI tool your agent needs.Free to start.

Start building