This tutorial covers how to add the [Speech MCP Server](https://github.com/Kvadratni/speech-mcp) as a Goose extension to enable real-time voice interaction, audio/video transcription, text-to-speech conversion, and multi-speaker audio generation.
[PortAudio](https://github.com/GoogleCloudPlatform/python-docs-samples/blob/main/scripts/readme-gen/templates/install_portaudio.tmpl.rst#install-portaudio) is required for PyAudio to capture audio from your microphone
[Launch the installer](goose://extension?cmd=uvx&&arg=-p&arg=3.10.14&arg=speech-mcp@latest&id=speech_mcp&name=Speech%20Interface&description=Voice%20interaction%20with%20audio%20visualization%20for%20Goose)
Note that you'll need [uv](https://docs.astral.sh/uv/#installation) installed on your system to run this command, as it uses `uvx`.
Before adding this extension, make sure [PortAudio](https://github.com/GoogleCloudPlatform/python-docs-samples/blob/main/scripts/readme-gen/templates/install_portaudio.tmpl.rst#install-portaudio) is installed on your system. **PortAudio is required** for PyAudio to capture audio from your microphone.
1. [Launch the installer](goose://extension?cmd=uvx&&arg=-p&arg=3.10.14&arg=speech-mcp@latest&id=speech_mcp&name=Speech%20Interface&description=Voice%20interaction%20with%20audio%20visualization%20for%20Goose)
2. Press `Yes` to confirm the installation
3. Click `Save Configuration`
4. Scroll to the top and click `Exit` from the upper left corner
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.
Here are some things you can say to activate the speech interface:
- “Goose, I don’t feel like typing today.”
- “Let’s talk using voice.”
- “Can we have a voice conversation?”
- “I’d 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_