Key features: * Real-time speech-to-text using Deepgram * High-quality text-to-speech with ElevenLabs * Intelligent conversation powered by OpenAI's GPT-4o * Smooth interactions with instant speech interruptions * Visual audio feedback with a dynamic visualizer
I created SpeakVerse to explore the potential of combining these powerful AI technologies and to provide a platform for developers to build upon. The project aims to push the boundaries of human-AI interaction and make conversational AI more accessible to developers and researchers. looking for feedback, suggestions, and contributions from the HN community. How can we improve SpeakVerse? What features would you like to see added? Feel free to create pull requests or open issues on our GitHub repository.