goose/documentation/docs/mcp/speech-mcp.md
dianed-square e7eb18b67a
Some checks are pending
Canary / bundle-desktop (push) Blocked by required conditions
Canary / bundle-desktop-linux (push) Blocked by required conditions
Canary / bundle-desktop-windows (push) Blocked by required conditions
Canary / Prepare Version (push) Waiting to run
Canary / build-cli (push) Blocked by required conditions
Canary / Upload Install Script (push) Blocked by required conditions
Canary / Release (push) Blocked by required conditions
CI / changes (push) Waiting to run
CI / Check Rust Code Format (push) Blocked by required conditions
CI / Build and Test Rust Project (push) Blocked by required conditions
CI / Lint Rust Code (push) Blocked by required conditions
CI / Check OpenAPI Schema is Up-to-Date (push) Blocked by required conditions
CI / Test and Lint Electron Desktop App (push) Blocked by required conditions
Deploy Documentation / deploy (push) Waiting to run
Live Provider Tests / check-fork (push) Waiting to run
Live Provider Tests / changes (push) Blocked by required conditions
Live Provider Tests / Build Release Binary (push) Blocked by required conditions
Live Provider Tests / Smoke Tests (push) Blocked by required conditions
Documentation Site Preview / deploy (push) Waiting to run
Publish Docker Image / docker (push) Waiting to run
docs: lowercase goose in remaining topics (#5861)
2025-11-24 11:05:41 -08:00

7.7 KiB
Raw Blame History

title description unlisted
Speech Extension Add Speech MCP Server as a goose Extension true

Unlist per https://github.com/block/goose/issues/5431

import Tabs from '@theme/Tabs'; import TabItem from '@theme/TabItem'; import YouTubeShortEmbed from '@site/src/components/YouTubeShortEmbed'; import GooseDesktopInstaller from '@site/src/components/GooseDesktopInstaller';

This tutorial covers how to add the Speech MCP Server as a goose extension to enable real-time voice interaction, audio/video transcription, text-to-speech conversion, and multi-speaker audio generation.

:::info Requirement PortAudio is required for PyAudio to capture audio from your microphone :::

:::tip TLDR Launch the installer Command

uvx -p 3.10.14 speech-mcp@latest
:::

Configuration

:::info Note that you'll need uv installed on your system to run this command, as it uses uvx.

Before adding this extension, make sure PortAudio is installed on your system. PortAudio is required for PyAudio to capture audio from your microphone. :::

1. Run the `configure` command: ```sh goose configure ```
  1. Choose to add a Command-line Extension
  ┌   goose-configure 
  │
  ◇  What would you like to configure?
  │  Add Extension (Connect to a new extension) 
  │
  ◆  What type of extension would you like to add?
  │  ○ Built-in Extension 
  // highlight-start    
  │  ● Command-line Extension (Run a local command or script)
  // highlight-end    
  │  ○ Remote Extension (SSE) 
  │  ○ Remote Extension (Streaming HTTP)
  1. Give your extension a name
  ┌   goose-configure 
  │
  ◇  What would you like to configure?
  │  Add Extension (Connect to a new extension) 
  │
  ◇  What type of extension would you like to add?
  │  Command-line Extension 
  │
  // highlight-start
  ◆  What would you like to call this extension?
  │  speech
  // highlight-end
  └ 
  1. Enter the command
  ┌   goose-configure 
  │
  ◇  What would you like to configure?
  │  Add Extension (Connect to a new extension) 
  │
  ◇  What type of extension would you like to add?
  │  Command-line Extension 
  │
  ◇  What would you like to call this extension?
  │  speech
  │
  // highlight-start
  ◆  What command should be run?
  │  uvx -p 3.10.14 speech-mcp@latest
  // highlight-end
  └ 
  1. Enter the number of seconds goose should wait for actions to complete before timing out. Default is 300s
 ┌   goose-configure 
 │
 ◇  What would you like to configure?
 │  Add Extension (Connect to a new extension) 
 │
 ◇  What type of extension would you like to add?
 │  Command-line Extension 
 │
 ◇  What would you like to call this extension?
 │  speech
 │
 ◇  What command should be run?
 │  uvx -p 3.10.14 speech-mcp@latest
 │
 // highlight-start
 ◆  Please set the timeout for this tool (in secs):
 │  300
 // highlight-end
 └ 
  1. Choose to add a description. If you select "Yes" here, you will be prompted to enter a description for the extension.
 ┌   goose-configure 
 │
 ◇  What would you like to configure?
 │  Add Extension (Connect to a new extension) 
 │
 ◇  What type of extension would you like to add?
 │  Command-line Extension 
 │
 ◇  What would you like to call this extension?
 │  speech
 │
 ◇  What command should be run?
 │  uvx -p 3.10.14 speech-mcp@latest
 │
 ◇  Please set the timeout for this tool (in secs):
 │  300
 │
 // highlight-start
 ◇  Would you like to add a description?
 │  No
 // highlight-end
 └ 
  1. Choose No when asked to add environment variables
 ┌   goose-configure 
 │
 ◇  What would you like to configure?
 │  Add Extension (Connect to a new extension) 
 │
 ◇  What type of extension would you like to add?
 │  Command-line Extension 
 │
 ◇  What would you like to call this extension?
 │  speech
 │
 ◇  What command should be run?
 │  uvx -p 3.10.14 speech-mcp@latest
 │
 ◇  Please set the timeout for this tool (in secs):
 │  300
 │
 ◇  Would you like to add a description?
 │  No
 │
 // highlight-start
 ◆  Would you like to add environment variables?
 │  No
 │
 // highlight-end
 └  Added speech extension

Example Usage

In this example, you'll see how to use goose with the Speech MCP Server Extension to turn voice commands into code. By speaking directly to goose, you can launch the speech interface, give a spoken prompt, and have goose generate and open a webpage based on your request.

This allows you to build with goose hands-free, making development more accessible and interactive.

1. Open a new session in goose Desktop 1. Open a terminal and start a new goose session:
goose session

goose Prompt

Here are some things you can say to activate the speech interface:

  • “goose, I dont feel like typing today.”
  • “Lets talk using voice.”
  • “Can we have a voice conversation?”
  • “Id like to speak instead of typing.”
  • “goose, launch the speech UI.”
goose I don't feel like talking today

goose Output

I understand! In that case, I can help you use voice commands instead. I'll launch the speech interface so you can speak your requests rather than type them

---- Launch Speech UI ----

goose Speech 🎙️

goose:

I've launched the speech interface. You can now speak your requests instead of typing. Just speak after you hear my voice and see the microphone activate. What would you like help with?

Max:

goose, lets create a simple page with the word 'vibes' on it and maybe change colors and make it move around the page and then open this page in the browser once you're done