Add voice interactions with Gemini Live and ros-mcp-server to Gemini example. #115
Conversation
tracelarue
changed the title
|
Thank you for your contribution, @tracelarue. I will give it a try soon. @rjohn-v — I’d suggest adding a client/ folder in the repository to store installation packages and runnable clients. This would help keep different client implementations (e.g., Gemini API client) and their installation steps organized in one place. I’m not sure I’d keep this under examples/. |
|
I connected issue #62 to this PR. |
Raises this error during installation, seems that I need a system-package: portaudio. I woudl recommend trying to include this into dependencies in the README.md + comamnd to install:
|
Couldn't run uv run on my WSL Ubuntu. Please specify that this works only on Ubuntu, will try on Ubuntu soon. |
|
@tracelarue @rjohn-v Another good next step would be to provide a |
There was a problem hiding this comment.
I would avoid creating a project inside the repository, but since this is a client project, it makes sense. Maybe we should move this example into a clients folder
There was a problem hiding this comment.
Would you like me to create a new folder for clients or leave it here for now? If yes, where should I create the clients folder?
There was a problem hiding this comment.
@rjohn-v what are your thoughts?
|
|
||
| 2. **Get Google API Key**: Visit [Google AI Studio](https://aistudio.google.com) and create an API key | ||
|
|
||
| 3. **Create `.env` file**: |
There was a problem hiding this comment.
Please specify where the .env file should be. In this folder?
|
|
||
| **Start Gemini Live:** | ||
| ```bash | ||
| cd ros-mcp-server/examples/2_gemini/gemini_live |
There was a problem hiding this comment.
Can we rename this to gemini_client.py or client_gemini.py?
|
|
||
| **Pre-requisites** See the [installation instructions](../../../docs/installation.md) for detailed setup steps. | ||
|
|
||
| **Tested In:** Ubuntu 22.04, Python 3.10, ROS2 Humble |
There was a problem hiding this comment.
Does this work also on WSL?
There was a problem hiding this comment.
I am unsure, I have not used WSL before.
There was a problem hiding this comment.
Ok, then let's make sure we specify it only works with Ubuntu.
There was a problem hiding this comment.
Ok, I'll specify that for now. I'll work on learning WSL so I can support it in the future.
There was a problem hiding this comment.
Unclear what is the role of this file. Do we needed as a dependencies or is it a "test_script"? If not strictly need we can consider removing it from the example.
This is the same error when I try to run mcp_handler.py |
|
@stex2005 Thank you for the review and feedback. I'll work on getting these changes and fixes implemented. |
|
@tracelarue wow, voice command sounds super cool. thanks for your contributions. I cannot wait for trying this feature soon! |
Gemini Live for low-latency bidirectional voice interactions with ros-mcp-server.