npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

livekit-plugin-parrot-stt

v0.1.0

Published

Ringg Parrot Speech-to-Text plugin for LiveKit Agents (Node.js)

Readme

livekit-plugin-parrot-stt

Ringg Parrot STT plugin for LiveKit Agents (Node.js / TypeScript).

It implements LiveKit's streaming STT interface (stt.STT + stt.SpeechStream) by speaking Ringg's WebSocket protocol directly, so it drops straight into a voice.AgentSession like any first-party plugin.

Ringg's official SDK (ringglabs) is Python-only. This plugin re-implements the same wire protocol in TypeScript.

Install

npm install livekit-plugin-parrot-stt
# peer deps (provided by your agent app):
npm install @livekit/agents @livekit/rtc-node

Usage

import { voice } from '@livekit/agents';
import * as ringg from 'livekit-plugin-parrot-stt';

const session = new voice.AgentSession({
  stt: new ringg.STT({
    // reads RINGG_STT_URL / RINGG_STT_API_KEY from the environment by default
    language: 'en', // 'hi' | 'en'
  }),
  // llm, tts, vad, ...
});

Standalone (no AgentSession):

import * as ringg from 'livekit-plugin-parrot-stt';

const stt = new ringg.STT({ url: 'wss://.../stt/v1/stream', apiKey: '...', language: 'en' });
const stream = stt.stream();

// push AudioFrames (Int16 PCM), then close the input:
for (const frame of frames) stream.pushFrame(frame);
stream.endInput();

for await (const ev of stream) {
  if (ev.type === /* FINAL_TRANSCRIPT */ 2) console.log(ev.alternatives?.[0]?.text);
}

Options

| Option | Env | Default | Notes | | --- | --- | --- | --- | | url | RINGG_STT_URL | wss://prod-api.ringg.ai/stt/v1/stream | Full WS URL. Confirm exact path with Ringg. | | apiKey | RINGG_STT_API_KEY | — | Sent inside the start JSON frame (not a header). | | language | RINGG_STT_LANGUAGE | en | hi | en | … | | sampleRate | RINGG_STT_SAMPLE_RATE | 16000 | LiveKit audio is resampled to this. | | encoding | RINGG_STT_ENCODING | int16 | int16 | linear16 | float32 | int32 | | mode | RINGG_STT_MODE | stream | stream = interim+final; on_final = finals only. | | enableCapPunc | — | true | Request capitalisation/punctuation. | | vadTailSilMs | — | 200 | Server-VAD trailing silence. | | vadConfidence | — | 0.55 | Server-VAD threshold. | | keepaliveIntervalMs | — | 30000 | JSON ping keepalive (0 disables). |

How it maps to LiveKit

  • Connect → send JSON start (auth = api_key) → wait for ready.
  • Stream raw binary PCM16 LE mono frames (20 ms chunks).
  • Ringg transcript events → INTERIM_TRANSCRIPT (is_final:false) / FINAL_TRANSCRIPT (is_final:true).
  • START_OF_SPEECH / END_OF_SPEECH are synthesised around transcript activity.
  • Endpointing uses Ringg's server-side VAD (mode:"stream"), which is the clean analog of the Pipecat integration through LiveKit's audio-only STT interface.

License

Apache-2.0