Build apps that let you have live conversations with AI. You can send real-time audio, video, and text over WebSockets. The AI responds instantly with speech, video, or text.
Features include voice activity detection to handle interruptions, function calling to use tools, and secure client tokens. You can also manage sessions and compress context.
Use the Python or JavaScript SDK to get started. This skill is for developers creating voice assistants, live translation, or interactive AI agents.
Global
mkdir -p ~/.claude/skills/gemini-live-api-devProject
mkdir -p .claude/skills/gemini-live-api-devSource Repository
Find Skillsvercel-labs/skills
Find and install the perfect skill to extend your AI agent
Microsoft Foundrymicrosoft/azure-skills
Build, deploy, and improve AI agents on Microsoft Foundry from start to finish
Azure Aimicrosoft/azure-skills
Search, transcribe, and analyze with Azure AI tools for smarter apps
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Build, deploy, and manage your Copilot SDK apps on Azure with ease
Triagemattpocock/skills
Triage issues with a state machine driven by clear roles and agent briefs
Handoffmattpocock/skills
Hand off your work to another AI agent with a clear summary
Image Editagentspace-so/runcomfy-agent-skills
Smart router picks the best AI model for your image editing needs
Agentspaceagentspace-so/skills
See your AI agent's live folder from any browser instantly