Skip to main content

​
Overview

NVIDIA Riva provides two STT service implementations: NvidiaSTTService for real-time streaming transcription using Parakeet models, and NvidiaSegmentedSTTService for segmented transcription using Canary models with advanced language support and enterprise-grade accuracy.

NVIDIA Riva STT API Reference

Pipecat’s API methods for NVIDIA Riva STT integration

Example Implementation

Complete example with NVIDIA services integration

NVIDIA Riva Documentation

Official NVIDIA Riva ASR documentation

NVIDIA Developer Portal

Access API keys and Riva services

​
Installation

To use NVIDIA Riva services, install the required dependency: 
pip install "pipecat-ai[nvidia]"

​
Prerequisites

​
NVIDIA Riva Setup

Before using NVIDIA Riva STT services, you need:
  1. NVIDIA Developer Account: Sign up at NVIDIA Developer Portal
  2. API Key: Generate an NVIDIA API key for Riva services
  3. Model Selection: Choose between Parakeet (streaming) and Canary (segmented) models

​
Required Environment Variables

  • NVIDIA_API_KEY: Your NVIDIA API key for authentication

​
Configuration

​
NvidiaSTTService

Real-time streaming transcription using NVIDIA Riva’s Parakeet models. Supports interim results and continuous audio processing.
​
api_key
str
required
NVIDIA API key for authentication.
​
server
str
default:"grpc.nvcf.nvidia.com:443"
NVIDIA Riva server address.
​
model_function_map
Mapping[str, str]
Mapping containing function_id and model_name for the ASR model.
​
sample_rate
int
default:"None"
Audio sample rate in Hz. When None, uses the pipeline’s configured sample rate.
​
params
InputParams
default:"None"
Configuration parameters. See NvidiaSTTService InputParams below.
​
use_ssl
bool
default:"True"
Whether to use SSL for the gRPC connection.

​
NvidiaSTTService InputParams

ParameterTypeDefaultDescription
languageLanguageLanguage.EN_USTarget language for transcription.

​
NvidiaSegmentedSTTService

Batch/segmented transcription using NVIDIA Riva’s Canary models. Processes complete audio segments after VAD detects speech boundaries.
​
api_key
str
required
NVIDIA API key for authentication.
​
server
str
default:"grpc.nvcf.nvidia.com:443"
NVIDIA Riva server address.
​
model_function_map
Mapping[str, str]
Mapping containing function_id and model_name for the ASR model.
​
sample_rate
int
default:"None"
Audio sample rate in Hz. When None, uses the pipeline’s configured sample rate.
​
params
InputParams
default:"None"
Configuration parameters. See NvidiaSegmentedSTTService InputParams below.
​
use_ssl
bool
default:"True"
Whether to use SSL for the gRPC connection.

​
NvidiaSegmentedSTTService InputParams

ParameterTypeDefaultDescription
languageLanguageLanguage.EN_USTarget language for transcription.
profanity_filterboolFalseWhether to filter profanity from results.
automatic_punctuationboolTrueWhether to add automatic punctuation.
verbatim_transcriptsboolFalseWhether to return verbatim transcripts.
boosted_lm_wordslist[str]NoneList of words to boost in the language model.
boosted_lm_scorefloat4.0Score boost for specified words.

​
Usage

​
Streaming with Parakeet

from pipecat.services.nvidia import NvidiaSTTService

stt = NvidiaSTTService(
    api_key=os.getenv("NVIDIA_API_KEY"),
)

​
Segmented with Canary

from pipecat.services.nvidia import NvidiaSegmentedSTTService
from pipecat.transcriptions.language import Language

stt = NvidiaSegmentedSTTService(
    api_key=os.getenv("NVIDIA_API_KEY"),
    params=NvidiaSegmentedSTTService.InputParams(
        language=Language.ES,
        automatic_punctuation=True,
        boosted_lm_words=["Pipecat", "NVIDIA"],
        boosted_lm_score=6.0,
    ),
)

​
Notes

  • Model cannot be changed after initialization: Use the model_function_map parameter in the constructor to specify the model and function ID.
  • Streaming vs segmented: NvidiaSTTService provides real-time interim and final results through continuous streaming. NvidiaSegmentedSTTService processes complete audio segments for higher accuracy.
  • Language support: Supports Arabic, English (US/GB), French, German, Hindi, Italian, Japanese, Korean, Portuguese (BR), Russian, and Spanish (ES/US).
  • Word boosting: Use boosted_lm_words and boosted_lm_score in the segmented service to improve recognition of domain-specific terms.