added inworld TTS plugin and example

examples/package.json

@@ -29,6 +29,7 @@
     "@livekit/agents-plugin-deepgram": "workspace:*",
     "@livekit/agents-plugin-elevenlabs": "workspace:*",
     "@livekit/agents-plugin-google": "workspace:*",
+    "@livekit/agents-plugin-inworld": "workspace:*",
     "@livekit/agents-plugin-livekit": "workspace:*",
     "@livekit/agents-plugin-neuphonic": "workspace:*",
     "@livekit/agents-plugin-openai": "workspace:*",

examples/src/inworld_tts.ts

@@ -0,0 +1,117 @@
+// SPDX-FileCopyrightText: 2025 LiveKit, Inc.
+//
+// SPDX-License-Identifier: Apache-2.0
+import {
+  type JobContext,
+  type JobProcess,
+  WorkerOptions,
+  cli,
+  defineAgent,
+  metrics,
+  voice,
+} from '@livekit/agents';
+import * as inworld from '@livekit/agents-plugin-inworld';
+import * as livekit from '@livekit/agents-plugin-livekit';
+import * as silero from '@livekit/agents-plugin-silero';
+import { BackgroundVoiceCancellation } from '@livekit/noise-cancellation-node';
+import { fileURLToPath } from 'node:url';
+
+export default defineAgent({
+  prewarm: async (proc: JobProcess) => {
+    proc.userData.vad = await silero.VAD.load();
+  },
+  entry: async (ctx: JobContext) => {
+    const agent = new voice.Agent({
+      instructions:
+        "You are a helpful assistant, you can hear the user's message and respond to it in 1-2 short sentences.",
+    });
+
+    // Create TTS instance
+    const tts = new inworld.TTS({
+      timestampType: 'WORD',
+      voice: 'Hades',
+      model: 'inworld-tts-1',
+      encoding: 'LINEAR16',
+      textNormalization: 'ON',
+      bitRate: 64000,
+      sampleRate: 24000,
+      speakingRate: 1.0,
+      temperature: 1.1,
+      bufferCharThreshold: 100,
+      maxBufferDelayMs: 3000,
+    });
+
+    // List available voices
+    tts
+      .listVoices()
+      .then((voices: inworld.Voice[]) => {
+        console.log(`[Inworld TTS] ${voices.length} voices available in this workspace`);
+        if (voices.length > 0) {
+          console.log(
+            '[Inworld TTS] Logging information for first voice:',
+            JSON.stringify(voices[0], null, 2),
+          );
+        }
+      })
+      .catch((err: Error) => {
+        console.error('[Inworld TTS] Failed to list voices:', err);
+      });
+
+    const session = new voice.AgentSession({
+      // Speech-to-text (STT) is your agent's ears, turning the user's speech into text that the LLM can understand
+      // See all available models at https://docs.livekit.io/agents/models/stt/
+      stt: 'assemblyai/universal-streaming:en',
+      // A Large Language Model (LLM) is your agent's brain, processing user input and generating a response
+      // See all available models at https://docs.livekit.io/agents/models/llm/
+      llm: 'openai/gpt-4.1-mini',
+      // Text-to-speech (TTS) is your agent's voice, turning the LLM's text into speech that the user can hear
+      // See all available models as well as voice selections at https://docs.livekit.io/agents/models/tts/
+      tts,
+      // VAD and turn detection are used to determine when the user is speaking and when the agent should respond
+      // See more at https://docs.livekit.io/agents/build/turns
+      vad: ctx.proc.userData.vad! as silero.VAD,
+      turnDetection: new livekit.turnDetector.MultilingualModel(),
+      // to use realtime model, replace the stt, llm, tts and vad with the following
+      // llm: new openai.realtime.RealtimeModel(),
+      voiceOptions: {
+        // allow the LLM to generate a response while waiting for the end of turn
+        preemptiveGeneration: true,
+      },
+    });
+
+    // timestamp handling (if enabled)
+    session.tts!.on('alignment' as any, (data: any) => {
+      if (data.wordAlignment) {
+        const { words, starts, ends } = data.wordAlignment;
+        for (let i = 0; i < words.length; i++) {
+          console.log(`[Inworld TTS] Word: "${words[i]}", Start: ${starts[i]}, End: ${ends[i]}`);
+        }
+      }
+      if (data.characterAlignment) {
+        const { chars, starts, ends } = data.characterAlignment;
+        for (let i = 0; i < chars.length; i++) {
+          console.log(`[Inworld TTS] Char: "${chars[i]}", Start: ${starts[i]}, End: ${ends[i]}`);
+        }
+      }
+    });
+
+    const usageCollector = new metrics.UsageCollector();
+
+    session.on(voice.AgentSessionEventTypes.MetricsCollected, (ev) => {
+      metrics.logMetrics(ev.metrics);
+      usageCollector.collect(ev.metrics);
+    });
+
+    await session.start({
+      agent,
+      room: ctx.room,
+      inputOptions: {
+        noiseCancellation: BackgroundVoiceCancellation(),
+      },
+    });
+
+    session.say('Hello, how can I help you today?');
+  },
+});
+
+cli.runApp(new WorkerOptions({ agent: fileURLToPath(import.meta.url) }));

plugins/inworld/api-extractor.json

@@ -0,0 +1,21 @@
+/**
+ * Config file for API Extractor.  For more info, please visit: https://api-extractor.com
+ */
+{
+  "$schema": "https://developer.microsoft.com/json-schemas/api-extractor/v7/api-extractor.schema.json",
+
+  /**
+   * Optionally specifies another JSON config file that this file extends from.  This provides a way for
+   * standard settings to be shared across multiple projects.
+   *
+   * If the path starts with "./" or "../", the path is resolved relative to the folder of the file that contains
+   * the "extends" field.  Otherwise, the first path segment is interpreted as an NPM package name, and will be
+   * resolved using NodeJS require().
+   *
+   * SUPPORTED TOKENS: none
+   * DEFAULT VALUE: ""
+   */
+  "extends": "../../api-extractor-shared.json",
+  "mainEntryPointFilePath": "./dist/index.d.ts"
+}
+

plugins/inworld/package.json

@@ -0,0 +1,52 @@
+{
+  "name": "@livekit/agents-plugin-inworld",
+  "version": "0.1.0",
+  "description": "Inworld plugin for LiveKit Node Agents",
+  "main": "dist/index.js",
+  "require": "dist/index.cjs",
+  "types": "dist/index.d.ts",
+  "exports": {
+    "import": {
+      "types": "./dist/index.d.ts",
+      "default": "./dist/index.js"
+    },
+    "require": {
+      "types": "./dist/index.d.cts",
+      "default": "./dist/index.cjs"
+    }
+  },
+  "author": "LiveKit",
+  "type": "module",
+  "repository": "[email protected]:livekit/agents-js.git",
+  "license": "Apache-2.0",
+  "files": [
+    "dist",
+    "src",
+    "README.md"
+  ],
+  "scripts": {
+    "build": "tsup --onSuccess \"pnpm build:types\"",
+    "build:types": "tsc --declaration --emitDeclarationOnly && node ../../scripts/copyDeclarationOutput.js",
+    "clean": "rm -rf dist",
+    "clean:build": "pnpm clean && pnpm build",
+    "lint": "eslint -f unix \"src/**/*.{ts,js}\"",
+    "api:check": "api-extractor run --typescript-compiler-folder ../../node_modules/typescript",
+    "api:update": "api-extractor run --local --typescript-compiler-folder ../../node_modules/typescript --verbose"
+  },
+  "devDependencies": {
+    "@livekit/agents": "workspace:*",
+    "@livekit/rtc-node": "^0.13.12",
+    "@microsoft/api-extractor": "^7.35.0",
+    "@types/ws": "^8.5.10",
+    "tsup": "^8.3.5",
+    "typescript": "^5.0.0"
+  },
+  "dependencies": {
+    "ws": "^8.16.0"
+  },
+  "peerDependencies": {
+    "@livekit/agents": "workspace:*",
+    "@livekit/rtc-node": "^0.13.12"
+  }
+}
+

plugins/inworld/src/index.ts

@@ -0,0 +1,19 @@
+// SPDX-FileCopyrightText: 2024 LiveKit, Inc.
+//
+// SPDX-License-Identifier: Apache-2.0
+import { Plugin } from '@livekit/agents';
+import './tts.js';
+
+export * from './tts.js';
+
+class InworldPlugin extends Plugin {
+  constructor() {
+    super({
+      title: 'Inworld',
+      version: '0.1.0',
+      package: '@livekit/agents-plugin-inworld',
+    });
+  }
+}
+
+Plugin.registerPlugin(new InworldPlugin());