How to connect Typecast 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 Typecast account to Cowork via Composio Connect, enabling it to generate voiceover for product demo script, find warm narrator voices for ads, update custom voices for brand videos, and more such actions on your behalf without compromising your account security.

Connecting Typecast 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 Typecast through MCP without you sharing account credentials directly with the agent.

The Typecast MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Typecast account. It provides structured and secure access to speech generation, voice discovery, voice details, and subscription usage, so your agent can create expressive audio, compose speech sequences, generate timestamps, recommend voices, and check account usage on your behalf.

• Text to speech generation: Have your agent turn text into complete WAV or MP3 audio using an available Typecast voice.
• Speech composition: Direct your agent to create one audio file from an ordered mix of spoken passages and pauses.
• Timed speech alignment: Instruct your agent to generate speech with word timestamps, character timestamps, or both for captions and synchronized experiences.
• Voice discovery and recommendations: Let the agent list available built-in and custom voices, filter them by traits and use cases, recommend matches from a natural-language description, and review voice details, models, and emotions.
• Plan and usage checks: Have your agent check your Typecast plan, credit usage, concurrency limit, and custom voice allowance.