> ## Documentation Index
> Fetch the complete documentation index at: https://docs.zeroruntime.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# NVIDIA

> Use the NVIDIA Riva speech-to-text plugin in a Zero Runtime pipeline. Setup and usage in Python and JavaScript.

NVIDIA Riva is a **speech-to-text** plugin that provides GPU-accelerated, low-latency speech
recognition for the caller's audio.

## Setup

Set your NVIDIA API key in the worker environment. Generate a key from the [NVIDIA build portal](https://build.nvidia.com/):

```bash theme={null}
export NVIDIA_API_KEY=<key>
```

## Usage

Import the plugin and pass it to the pipeline's `stt` slot.

<CodeGroup>
  ```python Python theme={null}
  from zeroruntime.plugins import NvidiaSTT

  stt = NvidiaSTT()

  # Pipeline(stt=stt, ...)
  ```

  ```typescript Node JS theme={null}
  import { NvidiaSTT } from '@zeroruntime/js-sdk/plugins';

  const stt = NvidiaSTT();

  // Pipeline({ stt, ... })
  ```
</CodeGroup>

## Parameters

| Parameter | Type | Default | Description |
| - | - | - | - |
| `api_key` | `str \| None` | `None` | NVIDIA API key. Falls back to the `NVIDIA_API_KEY` environment variable when unset. |
| `model` | `str` | `"parakeet-1.1b-en-US-asr-streaming-silero-vad-sortformer"` | Riva/NIM ASR model used for transcription (Parakeet 1.1B with Silero VAD + Sortformer diarization). |
| `server` | `str` | `"grpc.nvcf.nvidia.com:443"` | Riva gRPC endpoint. |
| `function_id` | `str` | `""` | NVCF function ID for the hosted model. |
| `language_code` | `str` | `"en-US"` | BCP-47 language tag of the caller's speech. |
| `sample_rate` | `int` | `16000` | Sample rate (Hz) of the input audio. |
| `use_ssl` | `bool` | `True` | Use a TLS/SSL gRPC channel. |
| `profanity_filter` | `bool` | `False` | Mask profanity in transcripts. |
| `automatic_punctuation` | `bool` | `True` | Add punctuation to transcripts. |

Transcribed text passes to the [LLM](/runtime-sdk/plugins/llm/google) once
[turn detection](/runtime-sdk/plugins/turn-detection/namo) decides the caller has finished speaking.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.