NVIDIA Riva
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 retrieval-augmented generation (RAG) to transform chatbots into powerful multilingual assistants and avatars.
See Riva in Action
Try NVIDIA Riva Automatic Speech Recognition
Select the language and check out how Riva ASR delivers highly accurate transcription in real time by providing an input through your microphone or uploading a .wav file from your device.
Note: The duration of each sample is limited to 30 seconds.
Try NVIDIA Riva Text-to-Speech
Select a voice and type in a test sentence to hear Riva’s out-of-the-box English female or male voice.
Note: Input text is limited to 400 characters.
Use of Riva skills is subject to NVIDIA Riva terms of use. Your data will be used to improve NVIDIA products and services.
Ways to Get Started With NVIDIA Riva
Find the right tools to build and deploy fully customizable, multilingual speech and translation AI applications.
Try From Your Browser
Quickly experience NVIDIA Riva from your browser—without any setup—with sample data via API and UI-based demos for free.
Experience the NVIDIA API Catalog
Access Speech AI Workflows for Development
Accelerate development time with packaged speech AI workflows available as a free trial on NVIDIA LaunchPad.
Try the Workflows on LaunchPad
Deploy in Production
Move from pilot to production with the assurance of security, API stability, and support with NVIDIA AI Enterprise.
Contact Us About Purchasing Riva Apply for a 90-Day NVIDIA AI
Enterprise Evaluation
Introductory Resources
Quick-Start Guide
Get step-by-step instructions for deploying pretrained models as services on a local workstation and how to interact with them through a client.
Introductory Blog
Learn about Riva’s architecture, key features, and components for building speech and translation AI services.
Introductory Webinar
Build and deploy end-to-end speech and translation AI pipelines using Riva.
Use-Case Demo
See how Computacenter, Tarteel, Floatbot, Minerva CQ and others use Riva for multilingual transcription, translation, and voice of their agent assists, AI virtual assistants, and digital humans.
Development Starter Kits
Access everything you need to start developing your speech and translation AI application with Riva containers and models, including tutorials, notebooks, forums, release notes, and documentation.
Automatic Speech Recognition
Achieve high transcription accuracy for Arabic, English, French, German, Hindi, Italian, Japanese, Korean, Mandarin, Portuguese, Russian, and Spanish with state-of-the-art models pretrained on thousands of hours of audio on NVIDIA supercomputers.
Text-to-Speech
Customize across English, German, Italian, Mandarin, and Spanish TTS pipelines for the voice and intonation you want.
Neural Machine Translation
Integrate highly accurate text-to-text, speech-to-text, or speech-to-speech translation for up to 32 languages into your conversational application pipelines.
Demo Video Tutorials
Learn to set up and start using Riva—from accessing NVIDIA NGC and working with the Riva Skills Quick Start guide, to running inference with ASR, TTS, and NMT models.
The Basics of NVIDIA NGC
Watch VideoQuick Start Guide for Riva
Watch VideoExploring Riva’s Capabilities
Watch VideoSelf-Paced Training
Learn anytime, anywhere, with just a computer and an internet connection through the NVIDIA Deep Learning Institute (DLI).
Riva Speech API Demo
Take This DLI CourseGet Started With Highly Accurate Custom ASR for Speech AI
Take This DLI CourseNVIDIA platforms and application frameworks enable developers to build a wide array of AI applications. Consider potential algorithmic bias when choosing or creating the models being deployed. Also, work with the model’s developer to ensure that it meets the requirements for the relevant industry and use case; that the necessary instruction and documentation are provided to understand error rates, confidence intervals, and results; and that the model is being used under the conditions and in the manner intended.