# xAI

> Text-to-speech with xAI: XAITTSService over WebSocket, with word timestamps, and XAIHttpTTSService over HTTP.

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



## Overview [#overview]

* **`XAITTSService`**: streams text over a WebSocket and pushes audio as it arrives, with word timestamps from xAI's character timings.
* **`XAIHttpTTSService`**: one HTTP request per sentence.

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

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

  <Card title="xAI docs" href="https://docs.x.ai/developers/rest-api-reference/inference/voice">
    The voice API reference.
  </Card>
</Cards>

## Installation [#installation]

```bash
bun add @pipedog/xai
```

```ts
import { XAITTSService, XAIHttpTTSService } from "@pipedog/xai/tts";
```

## Prerequisites [#prerequisites]

* An xAI account and an API key from the [xAI console](https://console.x.ai/).
* Pass the key as `apiKey`. The examples read it from `XAI_API_KEY`.

## XAITTSService [#xaittsservice]

Connects to `wss://api.x.ai/v1/tts`.

### Configuration [#configuration]

| Option | Type | Required | Description |
|---|---|---|---|
| `apiKey` | `string` | yes | xAI API key for authentication. |
| `baseUrl` | `string \| undefined` | no | xAI TTS WebSocket endpoint. Defaults to "wss://api.x.ai/v1/tts". |
| `codec` | `string \| undefined` | no | Output audio codec. One of `pcm`, `wav`, `mulaw`, `alaw`. Defaults to `pcm` so emitted `TTSAudioRawFrame` objects need no decoding downstream. |
| `settings` | `XAIWebsocketTTSSettings \| null \| undefined` | no | Runtime-updatable settings. |
| `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`. |
| `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. |

### Settings [#settings]

Runtime-updatable settings, passed as `settings: new XAITTSService.Settings({...})`
(`XAIWebsocketTTSSettings`). Any setting you leave out keeps the default below.

| Setting                    | Type               | Default       | Description                                 |
| -------------------------- | ------------------ | ------------- | ------------------------------------------- |
| `model`                    | `string \| null`   | `null`        | Speech model. `null` leaves xAI's default.  |
| `voice`                    | `string`           | `"eve"`       | Voice.                                      |
| `language`                 | `Language \| null` | `Language.EN` | Language; `null` sends `"auto"`.            |
| `speed`                    | `number \| null`   | `null`        | Speed, 0.7 to 1.5.                          |
| `optimizeStreamingLatency` | `number \| null`   | `null`        | Latency optimization level: 0, 1 or 2.      |
| `textNormalization`        | `boolean \| null`  | `null`        | Normalize the text before synthesis.        |
| `withTimestamps`           | `boolean`          | `true`        | Word timestamps, pushed as `TTSTextFrame`s. |

### Usage [#usage]

```ts title="tts.ts"
import { TTSUpdateSettingsFrame } from "@pipedog/core/frames/frames";
import { XAIHttpTTSService, XAITTSService } from "@pipedog/xai/tts";

const tts = new XAITTSService({
  apiKey: process.env.XAI_API_KEY ?? "",
  settings: new XAITTSService.Settings({ voice: "eve" }),
});
```

Change settings mid-call with an `TTSUpdateSettingsFrame`:

```ts
// Queue it on the worker, or push it from a processor upstream of the service.
const update = new TTSUpdateSettingsFrame({
  delta: new XAITTSService.Settings({ speed: 1.1 }),
});
```

### Event handlers [#event-handlers]

| Event                 | Description              |
| --------------------- | ------------------------ |
| `on_connected`        | The WebSocket connected. |
| `on_disconnected`     | The WebSocket closed.    |
| `on_connection_error` | The connection failed.   |

### Notes [#notes]

* `codec` is `"pcm"` by default; `wav`, `mulaw` and `alaw` also work.
* The end of a turn sends `text.done`; an interruption sends `text.clear` and keeps the socket open.
* Settings are query parameters of the connection, so any settings change reconnects.

## XAIHttpTTSService [#xaihttpttsservice]

Posts each sentence to `https://api.x.ai/v1/tts`.

### Configuration [#configuration-1]

| Option | Type | Required | Description |
|---|---|---|---|
| `enableDirectMode` | `boolean \| undefined` | no | Process frames immediately instead of using internal queues. |
| `metrics` | `FrameProcessorMetrics \| null \| undefined` | no | Optional metrics collector for this processor. |
| `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. |
| `apiKey` | `string` | yes | xAI API key for authentication. |
| `baseUrl` | `string \| undefined` | no | xAI TTS endpoint. Defaults to "https://api.x.ai/v1/tts". |
| `encoding` | `string \| null \| undefined` | no | Output encoding format. Defaults to "pcm". |
| `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: upstream takes an optional shared `aiohttp_session`. |
| `settings` | `XAITTSSettings \| null \| undefined` | no | Runtime-updatable settings. |
| `name` | `string \| null \| undefined` | no | Custom name; defaults to `ClassName#count`. |
| `taskManager` | `BaseTaskManager \| null \| undefined` | no | Task manager for handling tasks. |
| `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. |
| `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. |

### Settings [#settings-1]

Runtime-updatable settings, passed as `settings: new XAIHttpTTSService.Settings({...})`
(`XAITTSSettings`). Any setting you leave out keeps the default below.

| Setting                    | Type               | Default       | Description                                |
| -------------------------- | ------------------ | ------------- | ------------------------------------------ |
| `model`                    | `string \| null`   | `null`        | Speech model. `null` leaves xAI's default. |
| `voice`                    | `string`           | `"eve"`       | Voice.                                     |
| `language`                 | `Language \| null` | `Language.EN` | Language; `null` sends `"auto"`.           |
| `speed`                    | `number \| null`   | `null`        | Speed, 0.7 to 1.5.                         |
| `optimizeStreamingLatency` | `number \| null`   | `null`        | Latency optimization level: 0, 1 or 2.     |
| `textNormalization`        | `boolean \| null`  | `null`        | Normalize the text before synthesis.       |

### Usage [#usage-1]

```ts
const xAIHttpTTSService = new XAIHttpTTSService({
  apiKey: process.env.XAI_API_KEY ?? "",
  settings: new XAIHttpTTSService.Settings({ voice: "eve" }),
});
```

### Notes [#notes-1]

* `fetch` replaces the global `fetch` (upstream takes an aiohttp session).
* `encoding` is `"pcm"` by default.

## 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/xai/package.json`: ✅ means the compat smoke test passes on that runtime.

* HTTP goes through `fetch` and the WebSocket through the core `websocketConnect`. Both work on Bun, Node, Deno and Cloudflare Workers.
* Tested against local servers, as upstream's tests do, not against xAI itself.