NVIDIA® Riva is a set of GPU-accelerated multilingual speech and translation microservices for building fully customizable, real-time conversational AI pipelines. Riva includes automatic speech recognition (ASR), text-to-speech (TTS), and neural machine translation (NMT) and is deployable in all clouds, in data centers, at the edge, or on embedded devices. With Riva, organizations can add speech and translation capabilities with large language models (LLMs) and retrieved-augmented generation (RAG) to transform chatbots into powerful multilingual assistants and avatars.
Riva is part of the NVIDIA AI Enterprise software platform, is available for $1 per GPU hour. Contact NVIDIA for special pricing for alternative GPU options or private offers. Link