Integrates real-time Retell AI voice calling and WebRTC capabilities into Next.js chat interfaces.
Voice Retell is a specialized skill that enables seamless browser-based voice communication within AI-powered web applications. It leverages the Retell AI SDK to provide a full-duplex WebRTC voice experience, including a "Switch to voice" UI toggle, server-side token management, and real-time transcript bridging. By automatically syncing voice transcripts back into the existing chat history, it ensures a unified multi-modal user experience where conversations can flow effortlessly between text and speech while maintaining a single source of truth for the conversation log.
주요 기능
01Ready-to-use UI components including voice overlays and mute controls
02Unified chat history with automatic voice-to-text transcript bridging
033 GitHub stars
04Real-time WebRTC voice streaming via Retell AI integration
05Secure server-side web call token generation and session management
06Dynamic visual feedback for agent speaking and listening states
사용 사례
01Enhancing accessibility by providing a voice-first interface for complex web applications
02Building interactive language learning apps with real-time speech feedback
03Adding a voice-enabled AI assistant to a customer support dashboard
