nvidia-riva-client
Python implementation of the Riva Client API
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires a running NVIDIA Riva server; audio I/O features (microphone, speaker) require PyAudio installed separately via conda.
- 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 · maintenance · safety
MIT (permissive) — MIT license permits unrestricted use, modification, and distribution with minimal restrictions, making it suitable for both open-source and commercial projects.
last release 2026-08-13 (1 days) · last repo commit 2026-08-13 · 138 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 570,249 downloads/mo, #5,956 on PyPI
Alternatives
Verify before relying
pip install nvidia-riva-client
from riva.client import ASRService
asr_service = ASRService()
transcript = asr_service.transcribe_file('audio.wav')- 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
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 on it.
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
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.
Requires a running NVIDIA Riva server; audio I/O features (microphone, speaker) require PyAudio installed separately via conda.
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')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
| License | MIT permissive |
| Python support | Supports the current Python release >=3.7 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 4 packagesgrpciogrpcio-toolswebsocketsprotobuf |
| Maintenance | Actively maintained 1 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 570,249 / month, #5,956 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersProgramming Language :: Python :: 3 |
Evidence: nvidia_riva_client-2.27.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “speech recognition client”
- nvidia-riva-clientClient library for NVIDIA Riva, a GPU-accelerated Speech AI SDK…
- deepgram-sdkOfficial Python SDK for Deepgram's speech recognition,…
- google-cloud-speechProvides a Python client for Google Cloud Speech-to-Text, converting…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also nemo-toolkit · SpeechRecognition · livekit-plugins-soniox · openai-whisper · nlpaug · sherpa-onnx-core · sherpa-onnx · rev-ai · google-cloud-texttospeech · TTS