Inworld

OverviewCopy Anchor Link

pipedog ports both of Pipecat's Inworld text-to-speech services:

• InworldTTSService: Inworld TTS over a bidirectional WebSocket, with several audio contexts on one connection and word-level timestamps. Lowest latency.
• InworldHttpTTSService: Inworld TTS over HTTP, streaming (/tts/v1/voice:stream) or in one piece (/tts/v1/voice), also with word-level timestamps.

InstallationCopy Anchor Link

bun add @pipedog/inworld

import { InworldHttpTTSService, InworldTTSService } from "@pipedog/inworld/tts";

PrerequisitesCopy Anchor Link

• An Inworld account and an API key from the Inworld portal.
• Pass the key as apiKey (the Base64 key Inworld gives you). The examples read it from INWORLD_API_KEY.

InworldTTSServiceCopy Anchor Link

ConfigurationCopy Anchor Link

SettingsCopy Anchor Link

Runtime-updatable settings, passed as settings: new InworldTTSService.Settings({...}) (InworldTTSSettings). Any setting you leave out keeps the default below. InworldHttpTTSService uses the same settings class.

UsageCopy Anchor Link

import { TTSUpdateSettingsFrame } from "@pipedog/core/frames/frames";
import { Language } from "@pipedog/core/transcriptions/language";
import { InworldHttpTTSService, InworldTTSService } from "@pipedog/inworld/tts";

const tts = new InworldTTSService({
  apiKey: process.env.INWORLD_API_KEY ?? "",
  settings: new InworldTTSService.Settings({
    voice: "Ashley",
    model: "inworld-tts-2",
    language: Language.EN,
    deliveryMode: "BALANCED",
  }),
});

Change the voice mid-call with a TTSUpdateSettingsFrame:

// Applies from the next context the service opens.
const update = new TTSUpdateSettingsFrame({
  delta: new InworldTTSService.Settings({ voice: "Dennis", temperature: 0.9 }),
});

InworldHttpTTSServiceCopy Anchor Link

ConfigurationCopy Anchor Link

UsageCopy Anchor Link

const httpTts = new InworldHttpTTSService({
  apiKey: process.env.INWORLD_API_KEY ?? "",
  // false posts to /tts/v1/voice and gets the audio in one piece.
  streaming: true,
  settings: new InworldHttpTTSService.Settings({ voice: "Ashley", speakingRate: 1.1 }),
});

NotesCopy Anchor Link

• Both output PCM at the pipeline's sample rate and push TTSTextFrames aligned to Inworld's word timestamps. When no timestamps arrive, the text is pushed as a whole.
• InworldTTSService lets the server decide when to flush buffered text (autoMode, on by default) and closes a context on interruption.

Runtime notesCopy Anchor Link

Generated from pipecat.runtimes and pipecat.compat in packages/inworld/package.json: ✅ means the compat smoke test passes on that runtime.

• InworldTTSService opens its socket with websocketConnect() from core, with the key in the Authorization header (through fetch on Cloudflare Workers). InworldHttpTTSService uses the global fetch; pass fetch to use another one (upstream takes an aiohttp session).
• Deprecated options are not ported: voiceId, model and params (InputParams) on the constructor, and aggregateSentences. The WebSocket buffer settings that only params could set always use their defaults.