How to connect Speechmatics to Claude Cowork

Cowork is Anthropic's AI agent for knowledge work. Think of it as Claude Code for everything else. It works autonomously with your computer, local files, and applications to accomplish complex tasks.

This guide walks you through the easiest and most secure way to connect your Speechmatics account to Cowork via Composio Connect, enabling it to transcribe yesterday's customer interview recording, check status of latest transcription jobs, retrieve transcript for completed media job, and more such actions on your behalf without compromising your account security.

Connecting Speechmatics to Claude Cowork

1. Open Customize

In Claude Desktop, click Customize in the left sidebar, then select Connectors and click the + icon at the top.

2. Add the Composio MCP server

Click Add custom connector and paste in the Composio MCP server URL:

Claude Cowork is Anthropic's agent for general knowledge work. It can use your computer, files, and connected applications to complete longer-running tasks across your work tools.

With Composio Connect, Cowork can securely access apps like Speechmatics through MCP without you sharing account credentials directly with the agent.

The Speechmatics MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Speechmatics account. It provides structured and secure access to your audio and video transcription workflows, so your agent can create transcription jobs, monitor their progress, retrieve transcripts, manage jobs, and review usage on your behalf.

• Audio and video transcription: Have your agent submit publicly accessible audio or video for asynchronous transcription.
• Job monitoring and management: Let the agent list transcription jobs, check their status and processing errors, or delete jobs and their associated transcripts.
• Transcript retrieval: Direct your agent to retrieve completed transcripts as structured content, plain text, or subtitle text.
• Language and feature discovery: Instruct your agent to check supported languages, locales, domains, translation options, and language identification features before starting a job.
• Transcription usage reporting: Have your agent report transcription counts and processed audio duration for a selected UTC date range.