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

@plumbus/voice-elevenlabs

v0.1.1

Published

ElevenLabs TTS provider for @plumbus/voice.

Vulnerabilities

Powered byPowered by Snyk
  • 0High
  • 0Medium
  • 0Low

Links

Git

Maintainers

noam-rnoam-rmark125mark125

Keywords

Readme

@plumbus/voice-elevenlabs

ElevenLabs TTS for Plumbus voice. Register as tts.provider: 'elevenlabs' and stream via the official @elevenlabs/elevenlabs-js SDK — flash models with native delivery params, eleven_v3 with inline text tags (Hebrew-capable).

npm license peer: @plumbus/core 0.6.x peer: @plumbus/voice 0.4.x

What is this?

Plumbus is an AI-native, contract-driven TypeScript application framework. @plumbus/voice is the optional voice runtime.

@plumbus/voice-elevenlabs is the ElevenLabs TTS adapter. It exports ELEVENLABS_TTS_REGISTRATION for the voice provider registry and uses textToSpeech.stream() for both flash and eleven_v3.

Why?

The official ElevenLabs JS SDK is large (~21 MB). Keeping it in an opt-in add-on means apps that never use ElevenLabs never pull it. The previous untested WebSocket flash path was removed — this package is the supported path.

What you get

| Surface | What it does | |---|---| | ELEVENLABS_TTS_REGISTRATION | Factory + descriptor for createProviderRegistry({ tts: { elevenlabs: … } }). | | ELEVENLABS_TTS_DESCRIPTOR / ELEVENLABS_TTS_MODELS | Catalog entry (flash capabilities) and static model list. | | createElevenLabsCapabilities / DEFAULT_ELEVENLABS_TTS_MODEL_ID | Capability helpers for catalog / config. | | ELEVENLABS_VOICE_PRICING | Pricing rows for voice cost estimation. | | resolveCredentialsFromEnv | Reads ELEVENLABS_API_KEY / optional ELEVENLABS_BASE_URL. |

Status

Optional add-on of @plumbus/voice 0.4.x and @plumbus/core 0.6.x. Implements official-SDK streaming TTS for flash and eleven_v3. Install alone does not register the provider.

Install

pnpm add @plumbus/voice @plumbus/voice-elevenlabs

Peers (copy literals): @plumbus/core 0.6.x, @plumbus/voice 0.4.x.

Env: ELEVENLABS_API_KEY (optional ELEVENLABS_BASE_URL).

Quick start

import { createProviderRegistry, defineVoice, registerVoiceRoutes } from '@plumbus/voice';
import { ELEVENLABS_TTS_REGISTRATION } from '@plumbus/voice-elevenlabs';
import { onRoutesRegistered } from '@plumbus/core';

export const voiceProviderRegistry = createProviderRegistry({
  tts: { elevenlabs: ELEVENLABS_TTS_REGISTRATION },
});

export const supportVoice = defineVoice({
  name: 'support',
  access: { roles: ['user'] },
  transport: { provider: 'websocket', mode: 'pushToTalk' },
  stt: { provider: 'web-speech', languages: ['he-IL'] },
  tts: {
    provider: 'elevenlabs',
    model: 'eleven_v3',
    voiceId: process.env['ELEVENLABS_VOICE_ID'] ?? 'default',
    locale: 'he-IL',
  },
  brain: {
    async run(_ctx, args) {
      return { text: args.transcript ?? '' };
    },
  },
});

onRoutesRegistered((app, routeConfig) => {
  registerVoiceRoutes(app, routeConfig, [supportVoice], {
    registry: voiceProviderRegistry,
    providers: {
      providers: {
        websocket: {},
        'web-speech': {},
        elevenlabs: { apiKey: process.env['ELEVENLABS_API_KEY'] },
      },
    },
    sessionTokenSecret: process.env['VOICE_SESSION_TOKEN_SECRET'],
  });
});

For CLI/workers, export the same voiceProviderRegistry from app/voice/registry.ts.

Key gotchas

  • Explicit registration required — install alone does nothing.
  • Do not import @elevenlabs/elevenlabs-js in app code — this package owns the SDK boundary (lazy import on first synthesize / listVoices).
  • chunkLengthSchedule is not supported (no SDK equivalent on stream()).
  • Flash models use native delivery params; eleven_v3 uses inline text tags.

Documentation / Agent recipes

The Plumbus ecosystem

@plumbus/voice-elevenlabs is one package in the Plumbus framework. For the full list of packages and when to use each, see the Plumbus monorepo README.

Links

License

MIT