NVIDIA Riva

Build and deploy fully customizable speech AI applications.

NVIDIA Riva

Build and deploy fully customizable speech AI applications.

Speech AI skills for every industry.

 Speech AI skills—automatic speech recognition (ASR) and text-to-speech (TTS)—transform how enterprises interact with and support their customers across all industries. NVIDIA® Riva, part of the NVIDIA AI platform, provides state-of-the-art GPU-optimized workflows for building and deploying fully customizable, real-time AI pipelines for applications like contact center agent assists, virtual assistants, digital avatars, brand voices, and video conferencing transcription. With Riva, you can adapt applications for your use case and deploy them in all clouds, in data centers, at the edge, or on embedded devices.

See world-class speech AI in action.

  • Speech to Text
  • Text to Speech

Try NVIDIA Riva automatic speech recognition.

In this demo, Riva ASR delivers highly accurate transcription in real time.

You can provide an input through your microphone or upload a .wav file from your device.

The duration of each sample is limited to 30 seconds.

Try saying something

Try NVIDIA Riva text-to-speech.

If you’re looking to add voice to your interactive virtual assistant, modern home device, or reading assistant for people with a reading disability or visual impairment, try Riva’s out-of-the-box (OOTB) English female or male voice.

Hear the human-like expressive voices created using Riva’s state-of-the-art (SOTA) neural speech synthesis models.

0 / 400

Your use of Riva Voice Recognition and Riva Text-to-Speech is subject to our Terms of Use. Your data will be used to improve NVIDIA products and services.

What is NVIDIA Riva?

Simple end-to-end workflow for speech AI applications.

Riva offers:

  • Pretrained speech AI SOTA models: ASR and TTS models are fully customizable for datasets and accelerating the development of domain-specific models by 10X.

  • High-performance inference: Inference is powered by NVIDIA TensorRT™ optimizations and served using the NVIDIA Triton™ Inference Server, both components of the NVIDIA AI platform.

  • Riva services: These are available as gRPC-based microservices for low-latency streaming and high-throughput offline use cases.

  • High scalability: Fully containerized, Riva can easily scale to hundreds and thousands of parallel streams.
End-to-End Speech AI Pipeline

Explore NVIDIA Riva benefits.

Out-of-the-Box Accuracy

High accuracy.

Offers pretrained state-of-the-art models trained on thousands of hours of audio on NVIDIA supercomputers.

Flexible Customization

Fully customizable.

Provides out-of-the-box models and flexible pipelines fine-tunable for your use case, industry, and domain.

Scalable Deployment

Runs anywhere at scale.

Supports scaling to hundreds of thousands of concurrent users in the cloud, in the data center, and at the edge.

Real-Time Performance

Real-time performance.

Achieves real-time performance far below the 300-millisecond threshold using powerful NVIDIA AI optimizations with NVIDIA TensorRT.

Enterprise Support

Enterprise support.

Ensures speech AI services with minimum downtime and maximum system utilization.

Get started with NVIDIA Riva.

You can get support for Riva through NVIDIA AI Enterprise software or download the containers and pretrained models for free.

Paid Enterprise Support

With NVIDIA AI Enterprise software, get support for large-scale deployments of Riva with NVIDIA Enterprise Support.

It includes:

  • Broad platform support, including full enterprise-grade support for multiple deployment options: bare metal, virtualized, containerized, and public cloud. 
  • Access to NVIDIA AI experts for guidance on configuration and performance, including access to engineering. Experts are available 8:00 a.m.–5:00 p.m. during local business hours.
  • Priority notifications of the latest security fixes and maintenance releases. 
  • Access to instructor-led workshops and self-paced training.

Free Containers and Models

NVIDIA Riva is available as a set of containers and pretrained models, free of charge, from NVIDIA NGC to members of the NVIDIA Developer Program.  

It includes:

  • Access to the developer forums where you can browse how-to questions and best practices.
  • ASR and TTS resources, including tutorials, sample apps, notebooks, and documentation.
  • A guide for deploying Riva pretrained models in the data center (local Docker or Kubernetes) or on embedded devices (local Docker), running a sample client, and customizing models.

Learn more about Riva ASR.

Speech recognition technology enables voice search on the internet, hands-free computing, voice commands to smart home devices and in-car assistants, medical note taking, contact center 24/7 virtual assistants, and phone call and video conferencing transcriptions for pattern and trends analytics. NVIDIA Riva automatic speech recognition (ASR) delivers world-class, accurate transcripts based on GPU-optimized models, fully customizable for any domain or deployment platform.

Key features of Riva ASR include:

  • Support for English, Spanish, Mandarin, Hindi, Russian, German, and French
  • Out-of-the-box models trained on a variety of domain-specific data for hundreds of thousands of hours on NVIDIA GPUs
  • Best-possible accuracy for different languages, accents, domains, vocabulary, and context by fine-tuning vocabulary, lexicon, acoustic, language, punctuation and inverse text normalization models
  • The ability to return streaming transcripts with automatic punctuation and world-level timestamps for hundreds of thousands of input audio streams
  • Word/Profanity filtering with customizable and effective offensive spoken words removal

Learn more about Riva TTS.

Text-to-speech produces voices that narrate e-books and documents, converse with humans as smart assistants or digital avatars, and are part of nearly all digital devices, including smartphones, tablets, and laptops. NVIDIA Riva text-to-speech (TTS) provides human-like synthetic voices based on state-of-the-art spectrogram generation and vocoder models. TTS pipelines are customizable and GPU-optimized to run efficiently in real time.

Key features of Riva TTS include:

  • SOTA models for generating expressive, human-like voices
  • Two out-of-the-box professional female and male voices for US English
  • Easy voice and accent fine-tuning with pitch, volume, and duration control for expressivity
  • 12X higher inference performance versus existing technologies

Fast-Track Your Riva Journey with NVIDIA LaunchPad

Get immediate access to NVIDIA Riva with free curated labs. Access step-by-step guided labs for speech AI with ready-to-use software, sample data, and applications.

Learn more about Riva embedded.

Riva embedded delivers real-time, reliable, and best-in-class accurate transcripts and expressive, human-like voices for conversational applications on devices such as delivery robots, intelligent touchless kiosks, vending machines, and virtual assistants for factory, shopping, medical, and smart home devices.

Key features of Riva embedded include:

  • SOTA, out-of-the-box ASR accuracy with full off-device customization for English, Spanish, Mandarin, Hindi, Russian, German, and French
  • Expressive OOTB professional female and male English voices deployable immediately on the device and with the ability to create new brand voices
  • Easy integration and reliable, real-time workstation performance in compact, on-device compute and memory
  • High privacy with speech data processing on the device
  • Deployable on NVIDIA Jetson AGX Xavier, Jetson Xavier NX, Jetson AGX Orin and Jetson Orin NX

The Developer Conference
for the Era of AI and the
Metaverse

Join us this September for a GTC that will inspire your next big idea. This is a don't miss opportunity to learn from experts and leaders in their fields on how AI is transforming industries and profoundly impacting the world. It all happens online SeptemberSep 19-22.

 

Stay up to date on the latest events and news.

Speech AI Summit

Free digital event, hosted by NVIDIA.

NVIDIA’s first annual Speech AI Summit takes place November 2, 2022, 9:00 a.m.–2:00 p.m. PT.  Join us for an engaging online conversation with experts from Google, Meta, NVIDIA, and more on trends and techniques in automatic speech recognition (ASR) and text-to-speech (TTS) technologies.

NVIDIA Speech AI Summit

NVIDIA Riva Sets New Bar for Fully Customizable Speech AI

At GTC, NVIDIA announced new additions to NVIDIA Riva including world-class automatic speech recognition in two new languages, Hindi and French. Riva also gained accuracy for English, Spanish, Russian, German, and Mandarin.

NVIDIA Riva Sets New Bar for Fully Customizable Speech AI

See performance benchmarks.

NVIDIA Riva Performance Benchmarks

Read customer stories.

NCS Customer Story

NCS used NVIDIA Riva TTS to customize a Singaporean voice with local pronunciation, tone, and accent for tens of thousands of Breeze—a driver’s companion app—monthly active users, with thousands accessing the app concurrently. 

T-Mobile Customer Story

T-Mobile uses NVIDIA Riva ASR in their call center to accurately transcribe customer conversations and provide real-time recommendations to help agents quickly resolve customer queries.

 Data Monsters Customer Story

Data Monsters added a speech pipeline to their Plabook app using NVIDIA Riva to help students read, assess phoneme-level accuracy, and provide individualized feedback.

RingCentral Customer Story

With NVIDIA Riva, RingCentral achieved unparalleled real-time transcription accuracy for video meetings, serving millions of users with diverse accents and domain-specific jargon.

Tarteel AI Customer Story

Tarteel uses NVIDIA Riva and NVIDIA NeMo to provide real-time feedback on Quran recitation at scale, enabling Muslims, instructors, content creators, and researchers to engage with the Quran.

 Floatbot Customer Story

Floatbot leverages NVIDIA Riva and NVIDIA TAO for their customized Singaporean English voice AI applications, automating call centers for insurance carriers and finance clients globally.

Leading adopters across all industries.

  • Customers
  • Partners
  • Service Delivery Partners
Artisight
Botify
Botpress
Interactions
Koreai
Lexistems
Malamute
Minervacq
Moneypenny
Pendulum
Plabook
Readai
Smartcow
Tarteel
Vectorventures
Computacenter
Data-Monsters
Instadeep
Quantiphi
Softserve
SVA

Ready to simplify your speech AI?

Free Trial of NVIDIA Riva Enterprsise

Try Riva for free on LaunchPad.

Access curated NVIDIA Riva labs to test and prototype your speech-based solutions.

Download NVIDIA Riva SDK

Download Riva containers and models for free.

Deploy NVIDIA Riva from the NVIDIA NGC.

Contact Us About NVIDIA Riva

Contact us.

Connect with experts to learn best practices for building and deploying speech AI applications.

Explore more resources.

Get an introduction.

Understand the key features in Riva that help you build speech AI services.

Explore the starter kit.

Get everything you need to start building your speech AI pipelines with NVIDIA Riva, including tutorials, Jupyter Notebooks, and documentation.

Watch a webinar.

Learn how NVIDIA AI empowers you to build and run world-class speech AI applications across thousands of streams in real time.

Check out an e-book.

Explore how to get started with integrating and deploying Riva ASR and TTS models in production with high-performance inference and minimal effort.

Sign up to receive the latest speech AI news from NVIDIA.

Fast-track your speech AI projects with Riva on Launchpad.