# Inworld

> Text-to-speech with InworldTTSService (WebSocket) and InworldHttpTTSService (HTTP).

Source: https://polvallverdu.github.io/pipedog/docs/services/tts/inworld/



## Overview [#overview]

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.

<Cards>
  <Card title="Upstream page" href="https://docs.pipecat.ai/api-reference/server/services/tts/inworld">
    Pipecat's documentation for the same services.
  </Card>

  <Card title="Source" href="https://github.com/polvallverdu/pipedog/tree/main/packages/inworld/src">
    `packages/inworld/src/tts.ts`.
  </Card>

  <Card title="Inworld docs" href="https://docs.inworld.ai/docs/tts/tts">
    Inworld TTS models and voices.
  </Card>
</Cards>

## Installation [#installation]

```bash
bun add @pipedog/inworld
```

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

## Prerequisites [#prerequisites]

* An Inworld account and an API key from the [Inworld portal](https://platform.inworld.ai).
* Pass the key as `apiKey` (the Base64 key Inworld gives you). The examples read it from
  `INWORLD_API_KEY`.

## InworldTTSService [#inworldttsservice]

### Configuration [#configuration]

| Option | Type | Required | Description |
|---|---|---|---|
| `apiKey` | `string` | yes | Inworld API key. |
| `url` | `string \| undefined` | no | URL of the Inworld WebSocket API. |
| `encoding` | `string \| undefined` | no | Audio encoding format. Defaults to "PCM". |
| `autoMode` | `boolean \| null \| undefined` | no | Whether to use auto mode. When enabled, the server controls flushing of buffered text. Defaults to true. |
| `applyTextNormalization` | `string \| null \| undefined` | no | Whether to apply text normalization. |
| `timestampTransportStrategy` | `InworldTimestampTransportStrategy \| null \| undefined` | no | Strategy for timestamp transport ("ASYNC" or "SYNC"). Defaults to "ASYNC". |
| `settings` | `InworldTTSSettings \| null \| undefined` | no | Runtime-updatable settings. Its given fields override the defaults (model "inworld-tts-2", voice "Ashley"). |
| `textAggregationMode` | `TextAggregationMode \| null \| undefined` | no | How to aggregate text before synthesis. |
| `appendTrailingSpace` | `boolean \| undefined` | no | Whether to append a trailing space to text before sending to TTS. Defaults to true. |
| `name` | `string \| null \| undefined` | no | Custom name; defaults to `ClassName#count`. |
| `taskManager` | `BaseTaskManager \| null \| undefined` | no | Task manager for handling tasks. |
| `enableDirectMode` | `boolean \| undefined` | no | Process frames immediately instead of using internal queues. |
| `metrics` | `FrameProcessorMetrics \| null \| undefined` | no | Optional metrics collector for this processor. |
| `reconnectBackoffMinWait` | `number \| undefined` | no | Minimum time, in seconds, to wait between reconnection attempts. |
| `reconnectBackoffMaxWait` | `number \| undefined` | no | Maximum time, in seconds, to wait between reconnection attempts. |
| `reconnectOnError` | `boolean \| undefined` | no | Whether to automatically reconnect on connection errors. |
| `wsCloseTimeout` | `number \| undefined` | no | Maximum time, in seconds, to wait for the peer to acknowledge the websocket closing handshake before dropping the connection. Applied to connections opened through `_websocketConnect()`. Increase it for peers that need longer to complete a graceful close. |
| `wsSendTimeout` | `number \| null \| undefined` | no | Maximum time, in seconds, a single send may wait on a peer that has stopped reading before the connection is dropped and the send throws `ConnectionClosedError`. Applied to connections opened through `_websocketConnect()`. Pass `null` to wait indefinitely. Defaults to `WS_SEND_TIMEOUT`. |
| `pushTextFrames` | `boolean \| undefined` | no | Whether to push TextFrames and LLMFullResponseEndFrames. |
| `pushStopFrames` | `boolean \| undefined` | no | Whether to automatically push TTSStoppedFrames. |
| `pushStartFrame` | `boolean \| undefined` | no | Whether to automatically create audio contexts and push TTSStartedFrames. When true, the base class handles `createAudioContext` and yields `TTSStartedFrame` before each synthesis call, so `runTts` implementations do not need to. |
| `stopFrameTimeoutS` | `number \| undefined` | no | Idle time before pushing TTSStoppedFrame when pushStopFrames is true. |
| `pushSilenceAfterStop` | `boolean \| undefined` | no | Whether to push silence audio after TTSStoppedFrame. |
| `silenceTimeS` | `number \| undefined` | no | Duration of silence to push when pushSilenceAfterStop is true. |
| `pauseFrameProcessing` | `boolean \| undefined` | no | Whether to hold incoming frames after a turn until its audio contexts end. Needed by services whose audio doesn't carry its request's context ID. |
| `maxConsecutiveZeroAudioContexts` | `number \| undefined` | no | How many consecutive TTS contexts may complete without producing any audio before the service is reported unable to do its job. Catches a provider that accepts requests and stays silent — an unknown voice ID, say — which no error ever surfaces. Every silent context reports an error the service can carry on from, whatever the limit is; on reaching the limit the service reports a permanent error instead, stops being given work, and the pipeline worker applies its `ProcessorUnusablePolicy`. Set to 0 to report silent contexts without ever writing the service off. |
| `sampleRate` | `number \| null \| undefined` | no | Output sample rate for generated audio. |
| `skipTextTypes` | `string[] \| null \| undefined` | no | List of text types that should not be spoken. |
| `textTransforms` | `[string, TextTransform][] \| null \| undefined` | no | A list of TextTransforms to transform text just before sending it to TTS. Each TextTransform takes the aggregated text and its type, and returns the transformed text. To register, provide a list of tuples of `[textType \| "*", transformFunction]`. |
| `transportDestination` | `string \| null \| undefined` | no | Destination for generated audio frames. |
| `reuseContextIdWithinTurn` | `boolean \| undefined` | no | Whether the service should reuse context IDs within the same turn. |
| `audioCache` | `TTSAudioCacheStore \| null \| undefined` | no | Where to keep synthesized audio for reuse (e.g. a shared `TTSAudioCache`). Text whose audio is in the cache is served from it, with no request to the provider. Lines get there through `warmAudioCache()`, and also from live synthesis when `cacheSynthesizedAudio` allows it. Only services that yield their audio from `runTts` (HTTP and streaming-RPC services, see `supportsAudioCache`) use it, and only in sentence aggregation mode. Defaults to null (no cache). pipedog only. |
| `cacheSynthesizedAudio` | `boolean \| ((text: string) => boolean) \| undefined` | no | Whether audio synthesized live is stored in `audioCache`, or a function that decides per text. Defaults to false: only warmed lines are stored, since a generated reply can repeat what the user said. pipedog only. |
| `audioCacheNamespace` | `string \| undefined` | no | Extra part of the cache key, for constructor options that change the audio but are not in `settings`. pipedog only. |

### Settings [#settings]

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.

| Setting        | Type                                           | Default           | Description                                         |
| -------------- | ---------------------------------------------- | ----------------- | --------------------------------------------------- |
| `voice`        | `string`                                       | `"Ashley"`        | Inworld voice id.                                   |
| `model`        | `string`                                       | `"inworld-tts-2"` | TTS model.                                          |
| `language`     | `Language \| null`                             | `null`            | Language of the text.                               |
| `speakingRate` | `number \| null`                               | `null`            | Speaking rate.                                      |
| `temperature`  | `number \| null`                               | `null`            | Sampling temperature.                               |
| `deliveryMode` | `"STABLE" \| "BALANCED" \| "CREATIVE" \| null` | `null`            | Stability vs. expressiveness. Only `inworld-tts-2`. |

### Usage [#usage]

```ts title="tts.ts"
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`:

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

## InworldHttpTTSService [#inworldhttpttsservice]

### Configuration [#configuration-1]

| Option | Type | Required | Description |
|---|---|---|---|
| `apiKey` | `string` | yes | Inworld API key. |
| `fetch` | `{ (input: RequestInfo \| URL, init?: RequestInit): Promise<Response>; (input: string \| URL \| Request, init?: RequestInit): Promise<Response>; } \| null \| undefined` | no | `fetch` used for HTTP requests. Defaults to the global `fetch`. DIVERGENCE: replaces upstream's required `aiohttp_session`. |
| `streaming` | `boolean \| undefined` | no | Whether to use streaming mode. Defaults to true. |
| `encoding` | `string \| undefined` | no | Audio encoding format. Defaults to "PCM". |
| `timestampTransportStrategy` | `InworldTimestampTransportStrategy \| null \| undefined` | no | Strategy for timestamp transport ("ASYNC" or "SYNC"). Defaults to "ASYNC". |
| `settings` | `InworldTTSSettings \| null \| undefined` | no | Runtime-updatable settings. Its given fields override the defaults (model "inworld-tts-2", voice "Ashley"). |
| `name` | `string \| null \| undefined` | no | Custom name; defaults to `ClassName#count`. |
| `taskManager` | `BaseTaskManager \| null \| undefined` | no | Task manager for handling tasks. |
| `enableDirectMode` | `boolean \| undefined` | no | Process frames immediately instead of using internal queues. |
| `metrics` | `FrameProcessorMetrics \| null \| undefined` | no | Optional metrics collector for this processor. |
| `textAggregationMode` | `TextAggregationMode \| null \| undefined` | no | How to aggregate incoming text before synthesis. `TextAggregationMode.SENTENCE` (default) buffers until sentence boundaries, `TextAggregationMode.TOKEN` streams tokens directly for lower latency. |
| `pushTextFrames` | `boolean \| undefined` | no | Whether to push TextFrames and LLMFullResponseEndFrames. |
| `pushStopFrames` | `boolean \| undefined` | no | Whether to automatically push TTSStoppedFrames. |
| `pushStartFrame` | `boolean \| undefined` | no | Whether to automatically create audio contexts and push TTSStartedFrames. When true, the base class handles `createAudioContext` and yields `TTSStartedFrame` before each synthesis call, so `runTts` implementations do not need to. |
| `stopFrameTimeoutS` | `number \| undefined` | no | Idle time before pushing TTSStoppedFrame when pushStopFrames is true. |
| `pushSilenceAfterStop` | `boolean \| undefined` | no | Whether to push silence audio after TTSStoppedFrame. |
| `silenceTimeS` | `number \| undefined` | no | Duration of silence to push when pushSilenceAfterStop is true. |
| `pauseFrameProcessing` | `boolean \| undefined` | no | Whether to hold incoming frames after a turn until its audio contexts end. Needed by services whose audio doesn't carry its request's context ID. |
| `maxConsecutiveZeroAudioContexts` | `number \| undefined` | no | How many consecutive TTS contexts may complete without producing any audio before the service is reported unable to do its job. Catches a provider that accepts requests and stays silent — an unknown voice ID, say — which no error ever surfaces. Every silent context reports an error the service can carry on from, whatever the limit is; on reaching the limit the service reports a permanent error instead, stops being given work, and the pipeline worker applies its `ProcessorUnusablePolicy`. Set to 0 to report silent contexts without ever writing the service off. |
| `appendTrailingSpace` | `boolean \| undefined` | no | Whether to append a trailing space to text before sending to TTS. This helps prevent some TTS services from vocalizing trailing punctuation (e.g., "dot"). Only applied in sentence aggregation mode; when streaming tokens, the incoming text's own whitespace is preserved. |
| `sampleRate` | `number \| null \| undefined` | no | Output sample rate for generated audio. |
| `skipTextTypes` | `string[] \| null \| undefined` | no | List of text types that should not be spoken. |
| `textTransforms` | `[string, TextTransform][] \| null \| undefined` | no | A list of TextTransforms to transform text just before sending it to TTS. Each TextTransform takes the aggregated text and its type, and returns the transformed text. To register, provide a list of tuples of `[textType \| "*", transformFunction]`. |
| `transportDestination` | `string \| null \| undefined` | no | Destination for generated audio frames. |
| `reuseContextIdWithinTurn` | `boolean \| undefined` | no | Whether the service should reuse context IDs within the same turn. |
| `audioCache` | `TTSAudioCacheStore \| null \| undefined` | no | Where to keep synthesized audio for reuse (e.g. a shared `TTSAudioCache`). Text whose audio is in the cache is served from it, with no request to the provider. Lines get there through `warmAudioCache()`, and also from live synthesis when `cacheSynthesizedAudio` allows it. Only services that yield their audio from `runTts` (HTTP and streaming-RPC services, see `supportsAudioCache`) use it, and only in sentence aggregation mode. Defaults to null (no cache). pipedog only. |
| `cacheSynthesizedAudio` | `boolean \| ((text: string) => boolean) \| undefined` | no | Whether audio synthesized live is stored in `audioCache`, or a function that decides per text. Defaults to false: only warmed lines are stored, since a generated reply can repeat what the user said. pipedog only. |
| `audioCacheNamespace` | `string \| undefined` | no | Extra part of the cache key, for constructor options that change the audio but are not in `settings`. pipedog only. |

### Usage [#usage-1]

```ts title="tts-http.ts"
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 }),
});
```

## Notes [#notes]

* Both output PCM at the pipeline's sample rate and push `TTSTextFrame`s 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 notes [#runtime-notes]

| Runtime            | Works | What it needs |
| ------------------ | ----- | ------------- |
| Bun                | ✅ yes | Nothing.      |
| Node.js            | ✅ yes | Nothing.      |
| Deno               | ✅ yes | Nothing.      |
| Cloudflare Workers | ✅ yes | Nothing.      |

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.