NVIDIA RIVA 2.0: What's New

NVIDIA® Riva is available with fully optimized pipelines for deploying real-time AI speech applications such as transcription and virtual assistants.

Riva highlights include:

  • World-class automatic speech recognition (ASR) and text-to-speech (TTS) models
  • ASR support for Spanish, German, and Russian in addition to English
  • Real-time Text-To-Speech pipeline with fine-grained control for expressivity
  • Easy workflow to fine-tune on custom data with NVIDIA TAO Toolkit
  • Ability to scale to hundreds of thousands of real-time streams
  • End-to-end workflow and tools to deploy services using single command

Download Now    Documentation     Forum

Introduction to Riva

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.

Get started

Introductory Blog

Learn about Riva’s architecture, key features, and components for building speech AI services.

Read blog

Introductory Webinar

Build and deploy end-to-end speech AI pipelines using NVIDIA Riva.

Watch webinar

Riva Developer Starter Kits

Everything you need to start developing your speech AI with NVIDIA Riva, including tutorials, notebooks, and documentation.

Automatic Speech Recognition

  • Getting Started with Riva ASR Video
  • 3-Part Blog for Training and Deployment
  • Contact Center Sample App
  • Jupyter Notebook for Fine Tuning your ASR model
  • ASR Documentation

Get Started

Text-to-Speech

  • Virtual Assistant Sample
  • Virtual Assistant with RASA Tutorial
  • Setting up a TTS Service Sample
  • Customizing TTS with SSML Sample
  • TTS Documentation

Get Started

Riva Enterprise

For large-scale deployment and full-service support, NVIDIA offers Riva Enterprise.


Download Now

Riva Tutorials


Riva Custom Voice Recorder Is Available in Early Access

Riva Custom Voice recorder is a tool powered by Riva Text-To-Speech pipeline to develop an AI voice clone.

Apply for Early Access
Ethical AI

NVIDIA’s 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. 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.