A demo for recording audio and video streams with simultaneous speech and face recognition.
Faster Whisper transcription with CTranslate2.
Speech to Text but with all the bells and whistles and most importantly AI!
A sound cloning tool with a web interface, using your voice or any sound to record audio.
Robust Speech Recognition via Large-Scale Weak Supervision
Witsy is a desktop AI assistant designed to enhance productivity across various applications.
Zero-shot voice conversion and singing voice conversion with real-time support and fine-tuning capabilities.
A powerful framework for building realtime voice AI agents.
Instant voice cloning by MIT and MyShell. Audio foundation model.
Fuse ChatTTS with OpenVoice to clone your personalized voice from a 10-second audio clip upload.
Real-time voice interactive digital human supporting customizable appearance and voice with low latency.
