Search Results for "tts"

NVIDIA NeMo, part of the NVIDIA AI platform, is a toolkit for building new state-of-the-art conversational AI models. NeMo has separate collections for Automatic Speech Recognition (ASR), Natural Language Processing (NLP), and Text-to-Speech (TTS) models. Each collection consists of prebuilt modules that include everything needed to train on your data. Every module can easily be customized, extended, and composed to create new conversational AI model architectures. Conversational AI architectures are typically large and require a lot of data and compute for training. NeMo uses PyTorch Lightning for easy and performant multi-GPU/multi-node mixed-precision training. ...

...Its goal is to provide a free and open-source alternative to big services like DialogFlow. You can chat with her by speaking (STT) or writing, she replies with a text message but you can enable her voice (TTS). Olivia can listen to you by saying “Hey Olivia” or clicking on the central button. She speaks to reply to you unless you've disabled her voice. Olivia respects your privacy. All the data used by Olivia is saved in your client. Olivia is organized in modules to facilitate the addition of new capabilities. These modules can be written in Go to execute multiple tasks. ...