# Async

> Text-to-speech with Async: AsyncAITTSService over WebSocket and AsyncAIHttpTTSService over HTTP streaming.

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



## Overview [#overview]

* **`AsyncAITTSService`**: keeps one WebSocket open and sends each sentence as a forced transcript on its own context, closing the context when its audio has played or the bot is interrupted.
* **`AsyncAIHttpTTSService`**: one HTTP request per sentence. The audio is collected and pushed as one frame.

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

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

  <Card title="Async docs" href="https://docs.async.com/text-to-speech-websocket-3477526w0.md">
    The WebSocket API reference.
  </Card>
</Cards>

## Installation [#installation]

```bash
bun add @pipedog/asyncai
```

```ts
import { AsyncAIHttpTTSService, AsyncAITTSService } from "@pipedog/asyncai/tts";
```

## Prerequisites [#prerequisites]

* An Async account, an API key and the UUID of a voice.
* Pass the key as `apiKey`. The examples read it from `ASYNC_API_KEY`.

## AsyncAITTSService [#asyncaittsservice]

Connects to `wss://api.async.com/text_to_speech/websocket/ws`, with the key and API version as query parameters.

### Configuration [#configuration]

| Option | Type | Required | Description |
|---|---|---|---|
| `apiKey` | `string` | yes | Async API key. |
| `version` | `string \| undefined` | no | Async API version. |
| `url` | `string \| undefined` | no | WebSocket URL for Async TTS API. |
| `encoding` | `string \| undefined` | no | Audio encoding format. |
| `container` | `string \| undefined` | no | Audio container format. |
| `settings` | `AsyncAITTSSettings \| 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 AsyncAITTSService.Settings({...})`
(`AsyncAITTSSettings`). Any setting you leave out keeps the default below. A change to `model`, `voice` or `language` opens a new session, because they are sent once, in the init message.

| Setting    | Type               | Default              | Description                          |
| ---------- | ------------------ | -------------------- | ------------------------------------ |
| `model`    | `string`           | `"async_flash_v1.5"` | Speech model.                        |
| `voice`    | `string \| null`   | `null`               | Voice UUID.                          |
| `language` | `Language \| null` | `null`               | Language, sent as a two-letter code. |

### Usage [#usage]

```ts title="tts.ts"
import { AsyncAIHttpTTSService, AsyncAITTSService } from "@pipedog/asyncai/tts";
import { TTSUpdateSettingsFrame } from "@pipedog/core/frames/frames";

const tts = new AsyncAITTSService({
  apiKey: process.env.ASYNC_API_KEY ?? "",
  settings: new AsyncAITTSService.Settings({
    model: "async_flash_v1.5",
    voice: "your-voice-uuid",
    language: "en",
  }),
});
```

Change settings mid-call with a `TTSUpdateSettingsFrame`:

```ts
// Opens a new session, since the voice is part of the init message.
const update = new TTSUpdateSettingsFrame({
  delta: new AsyncAITTSService.Settings({ voice: "another-voice-uuid" }),
});
```

### Event handlers [#event-handlers]

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

## AsyncAIHttpTTSService [#asyncaihttpttsservice]

Posts each sentence to `https://api.async.com/text_to_speech/streaming`.

### Configuration [#configuration-1]

| Option | Type | Required | Description |
|---|---|---|---|
| `apiKey` | `string` | yes | Async 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: upstream takes a required shared `aiohttp_session`. |
| `url` | `string \| undefined` | no | Base URL for Async API. |
| `version` | `string \| undefined` | no | API version string for Async API. |
| `encoding` | `string \| undefined` | no | Audio encoding format. |
| `container` | `string \| undefined` | no | Audio container format. |
| `settings` | `AsyncAITTSSettings \| 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. |
| `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. |

It takes the same settings as the WebSocket service.

### Usage [#usage-1]

```ts
const httpTts = new AsyncAIHttpTTSService({
  apiKey: process.env.ASYNC_API_KEY ?? "",
  settings: new AsyncAIHttpTTSService.Settings({ voice: "your-voice-uuid" }),
});
```

## Notes [#notes]

* Audio is raw `pcm_s16le` by default (`encoding` and `container` change that) at the pipeline's sample rate.
* The WebSocket sends a blank transcript every 10 seconds to keep the connection open.

## Runtime notes [#runtime-notes]

* The WebSocket opens through the core `websocketConnect`. Async takes the key in the URL, so no header is needed. The HTTP service uses the global `fetch`; pass `fetch` to use another one (upstream takes an aiohttp session). Both work on Bun, Node, Deno and Cloudflare Workers.
* The deprecated `params` (`InputParams`), `voiceId`, `model` and `aggregateSentences` options are not ported. Use `settings` and `textAggregationMode`.
* Tested against local servers, as upstream's tests do for the settings updates, not against Async itself.

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