NVIDIA® Riva is a GPU-accelerated speech AI—automatic speech recognition (ASR) and text-to-speech (TTS)—SDK for building fully customizable, real-time conversational AI pipelines and deploying them in clouds, in data centers, at the edge, or on embedded devices.
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.
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.
0 / 400
Use of Riva skills is subject to NVIDIA Riva terms of use. Your data will be used to improve NVIDIA products and services.
Achieve high transcription accuracy for English, Spanish, Mandarin, Hindi, Russian, Arabic, Japanese, Korean, German, Portuguese, French, and Italian and deploy two out-of-the-box expressive professional female and male voices for U.S. English with state-of-the-art models pretrained on thousands of hours of audio on NVIDIA supercomputers.
Customize across ASR pipelines for different languages, accents, domains, vocabulary, and context for the best possible accuracy for your use case and across TTS pipelines for the voice and intonation you want.
Provide consistent experiences to your customers for hundreds of thousands of input streams with higher inference performance versus existing technology and on deployment of your choice—in data centers, on premises, in the cloud, at the edge, or in embedded devices.
With NVIDIA AI Enterprise software, you get support for large-scale deployments of Riva.
It includes:
Reduce development time and improve accuracy and performance of speech AI solutions leveraging NVIDIA’s packaged AI workflows for Contact Center Intelligent Virtual Assistants and Speech Transcription, available with NVIDIA AI Enterprise.
These AI workflows include:
Riva is available as a set of containers and pretrained models, free of charge, from NVIDIA NGC™ for development purposes to members of the NVIDIA Developer Program.
Get unlimited usage on all clouds, access to NVIDIA AI experts, and long-term support for large-scale deployments with a purchase of NVIDIA Riva.
Accelerate development with packaged AI workflows for audio transcription and intelligent virtual assistants. Available with a purchase of NVIDIA Riva, these AI workflows include NVIDIA enterprise support, AI frameworks, and pretrained models, as well as resources such as Helm charts, Jupyter Notebooks, and documentation to help you jump-start building AI solutions.
Get 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.
NCS used NVIDIA Riva TTS to customize a Singaporean voice with local pronunciation, tone, and accent for thousands of Breeze—a driver’s companion app—monthly active users.
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 added a speech pipeline to their Plabook app using NVIDIA Riva to help students read, assess phoneme-level accuracy, and provide individualized feedback.
Artisight developed smart hospital solutions that automate check-in and notify waiting patients via voice-enabled kiosks. These solutions integrate a customized speech AI application and deliver real-time performance using GPU-accelerated NVIDIA Riva text-to-speech skills.
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 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 leverages NVIDIA Riva and NVIDIA TAO for their customized Singaporean English voice AI applications, automating call centers for insurance carriers and finance clients globally.
Join a data science and AI technology expert to learn about cutting-edge NVIDIA Riva speech AI solutions that are revolutionizing the industry, from virtual assistants and digital avatars for improved outreach, claims management, ordering, and provisioning to fraud detection systems for risk mitigation.
Join NVIDIA, AT&T, Kore.ai, Deloitte, Appen, and Sutherland to explore the benefits and challenges of using ASR, multi-language translation, and TTS to deliver faster and more accurate customer self-service, enhance live agent productivity, and boost operational efficiencies for enterprises.
Watch this on-demand webinar to learn how to build intelligent virtual assistants in the form of voice-enabled digital agents. We’ll showcase how to deploy flexible, fully customizable solutions to improve customer satisfaction.
Watch T-Mobile as they walk through their model development with NVIDIA NeMo, cloud deployment with NVIDIA Riva, their efforts to identify and remove bias in their models, and the future of speech-to-text at T-Mobile.
Understand the key features in Riva that help you build speech AI services.
Get everything you need to start building your speech AI pipelines with NVIDIA Riva, including tutorials, Jupyter Notebooks, and documentation.
Read a technical walkthrough on how to build and deploy speech AI applications using Riva.
Explore how to get started with integrating and deploying Riva ASR and TTS models in production with high-performance inference and minimal effort.
NVIDIA Privacy Policy