gemini-live-api
Generates a Gemini LiveAPI client service class in the user's chosen programming
by googleFree
Description
Gemini Live API is an agent skill for generating a client service class that connects to the Gemini Enterprise Live API over WebSockets. The generated client is written in the programming language you choose and handles bidirectional streaming, so audio, video and text can flow in both directions during a conversation. It authenticates with a bearer token obtained through Application Default Credentials, resumes sessions transparently when a connection drops, and exchanges ClientMessage and ServerMessage protocol buffer messages. The skill also produces a demo frontend and backend, so you can test the generated client interactively before you build on it. The demo covers text, audio, video, transcription and interruption handling, which is when a user speaks over the model. Before generating code, the skill lists the prerequisites that must be present on the host. It is aimed at developers who want to add a real-time voice or multimodal assistant to an application on Google Cloud and would rather scaffold a tested client than write the WebSocket protocol handling by hand. It is published by Google on skills.sh under the google skills repository, with about 4.8K installs. The skills.sh listing shows Gen Agent Trust Hub, Socket and Snyk all passing.…
Highlights
- Generates a Live API WebSocket client
- Bidirectional audio, video and text streaming
- Authentication with Application Default Credentials
- Transparent session resumption
- Demo frontend and backend for testing
Ratings & Reviews
No ratings yet
Be the first to rate gemini-live-api.
People also visit
gemini-live-api FAQ
What does the skill generate?
A client service class for the Gemini Enterprise Live API, in the programming language you choose, plus a demo frontend and backend.
What does the demo cover?
Text, audio, video, transcription and interruption handling.
How does it authenticate?
With a bearer token from Application Default Credentials.
Does it handle reconnects?
The generated client supports transparent session resumption.
How do I install it?
Run npx skills add https://github.com/google/skills --skill gemini-live-api.
What are the best gemini-live-api alternatives?
Popular alternatives to gemini-live-api include agent-platform-inference, agent-platform-tuning and gemini. See all gemini-live-api alternatives