Enable voice interactivity and AI presenter functionality for Next.js slide decks.
npx skills add https://github.com/josh-cooper/.claude --skill voice-agent
Please help me install this Agent Skill. Skill: voice-agent Source: https://github.com/josh-cooper/.claude/tree/main/skills/voice-agent Command: npx skills add https://github.com/josh-cooper/.claude --skill voice-agent
OpenAI Realtime API voice agent enables live, hands-free interaction within Next.js slide decks, turning static presentations into interactive experiences with AI presenters and voice navigation.
Start a session by wiring the Voice Agent provider, exposing the ephemeral token endpoint, and launching the presentation with voice interaction.
High-intent search queries and answers about installing and using this skill.
To add voice interactivity to a Next.js presentation, you wire a Voice Agent provider to handle real-time audio streaming and expose an ephemeral token endpoint. This enables AI-driven narration and live user Q&A within your slide deck.
Yes, the OpenAI Realtime API supports slide navigation via voice commands. It uses data channels specifically designed to trigger slide transitions and navigational tool integration during a live presentation session.
Real-time AI narration for slide decks works by streaming audio and text modalities through the OpenAI Realtime API. A token-based session workflow connects the AI presenter persona directly to your Next.js slides for live interaction.
Yes, WebRTC is required to build a voice agent for Next.js slides. It handles the real-time audio streaming necessary for hands-free interaction and seamless live narration between the user and the AI presenter.
The best way to enable live Q&A in a Next.js slide deck is by integrating a real-time voice agent. Launching the presentation with voice interaction allows the audience to ask questions and navigate slides using spoken commands.
Yes, the voice agent supports both audio and text modalities simultaneously. This dual-channel approach within the OpenAI Realtime API ensures accurate AI presenter responses and reliable voice-controlled slide navigation.
brivaroBuild real-time bidirectional streaming apps with the Gemini Live API.
dbmccoCreate single-file Keynote-style HTML slide decks with brand tokens and Gemini-generated visuals.
giosuetedeschi-specArchitect real-time voice AI applications with WebRTC and streaming audio APIs.
steipeteTranscribe audio files into text using the OpenAI Whisper API.
