nvidia-riva-client

What it is and what it does

nvidia-riva-client is a Python client library for interacting with NVIDIA Riva, a GPU-accelerated Speech AI platform. It provides three main service classes—ASRService for speech recognition, TTSService for text-to-speech, and NLPService for natural language processing—along with command-line scripts demonstrating streaming transcription, real-time WebSocket-based synthesis, and NLP tasks like intent detection, named entity recognition, and punctuation restoration.

The package depends on grpcio, grpcio-tools, websockets, and protobuf to communicate with a Riva server backend. It supports both streaming and offline modes, with optional real-time audio I/O via microphone and speaker (when PyAudio is installed separately). The library is actively maintained, supports Python 3.7 and later, and carries no known security vulnerabilities.

Use it for:

• Build a real-time speech transcription application that streams audio from a microphone and returns live transcripts with intermediate results.
• Integrate text-to-speech synthesis into a conversational AI system to generate spoken responses from text via WebSocket connections.
• Process batch audio files for offline transcription with optional word-boosting to improve accuracy on domain-specific terminology.
• Implement intent and slot recognition in a chatbot to extract user intent and entities from natural language queries.
• Add named entity recognition or punctuation restoration to a document processing pipeline for text normalization.
• Perform text classification on user inputs to route queries to appropriate downstream services.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Client library for NVIDIA Riva, a GPU-accelerated Speech AI SDK providing APIs for automatic speech recognition, text-to-speech synthesis, and natural language processing tasks.

Yes. The package is actively maintained, has low install friction, carries no known vulnerabilities, and offers a permissive MIT license. Install it if you need to build Speech AI applications with NVIDIA Riva; the main prerequisite is having a Riva server running and, for audio I/O features, PyAudio installed separately.

Install

nvidia-riva-client on PyPI

pip install nvidia-riva-client

uv add nvidia-riva-client

poetry add nvidia-riva-client

Installing nvidia-riva-client

Before you install

Low install friction with a pure Python wheel and four standard gRPC-based runtime dependencies. Active maintenance with a recent release and ongoing repository activity.

License in practice

MIT license permits unrestricted use, modification, and distribution with minimal restrictions, making it suitable for both open-source and commercial projects.

Quickstart

pip install nvidia-riva-client

from riva.client import ASRService

asr_service = ASRService()
transcript = asr_service.transcribe_file('audio.wav')

Requires a running NVIDIA Riva server; audio I/O features (microphone, speaker) require PyAudio installed separately via conda.

Verify before relying

• Whether Riva server setup complexity or licensing requirements affect practical deployment beyond the client library itself
• Performance characteristics and latency profiles for streaming vs. offline modes under typical workloads
• Compatibility with specific Riva server versions and any breaking changes across releases

Package facts

Evidence: nvidia_riva_client-2.27.0-py3-none-any.whl

Keywords: deep learning, machine learning, gpu, NLP, ASR, TTS, NMT, nvidia, speech, language, Riva, client

Tags

More Artificial Intelligence packages

Further reading