Open Source framework for voice and multimodal conversational AI

Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper

Speech To Speech: an effort for an open-sourced and modular GPT4-o

Easily train a good VC model with voice data <= 10 mins!

TypeScript-based library for real-time audio transcription, integrating OpenAI's Whisper model for accurate speech-to-text conversion.