# Together AI

> Text-to-speech with TogetherTTSService, streaming over Together AI's WebSocket API.

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



## Overview [#overview]

* **`TogetherTTSService`**: streams text over a WebSocket to Together's speech endpoint and pushes 24 kHz PCM audio as it arrives.

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

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

  <Card title="Together AI docs" href="https://docs.together.ai/">
    Voices, models and the WebSocket speech API.
  </Card>
</Cards>

## Installation [#installation]

```bash
bun add @pipedog/together
```

```ts
import { TogetherTTSService } from "@pipedog/together/tts";
```

## Prerequisites [#prerequisites]

* A Together AI account and an API key from [Together AI](https://together.ai/).
* Pass the key as `apiKey`. The examples read it from `TOGETHER_API_KEY`.

## TogetherTTSService [#togetherttsservice]

Connects to `wss://api.together.ai/v1/audio/speech/websocket`.

### Configuration [#configuration]

| Option | Type | Required | Description |
|---|---|---|---|
| `apiKey` | `string` | yes | Together AI API key for authentication. |
| `url` | `string \| undefined` | no | WebSocket URL for Together AI TTS API. Defaults to "wss://api.together.ai/v1/audio/speech/websocket". |
| `sampleRate` | `number \| null \| undefined` | no | Output sample rate for emitted PCM frames. Defaults to 24000; Together streams at 24 kHz and does not support other rates. |
| `settings` | `TogetherTTSSettings \| null \| undefined` | no | Runtime-updatable settings for the TTS service. |
| `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. |
| `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 TogetherTTSService.Settings({...})`
(`TogetherTTSSettings`). Any setting you leave out keeps the default below.

| Setting            | Type                              | Default                | Description                                                                      |
| ------------------ | --------------------------------- | ---------------------- | -------------------------------------------------------------------------------- |
| `model`            | `string`                          | `"hexgrad/Kokoro-82M"` | Speech model, sent in the URL.                                                   |
| `voice`            | `string`                          | `"af_heart"`           | Voice, sent in the URL.                                                          |
| `language`         | `Language \| null`                | `Language.EN`          | Language, sent in the URL.                                                       |
| `maxPartialLength` | `number \| null`                  | `null`                 | Maximum partial text length for streaming (`max_partial_length`).                |
| `extraParams`      | `Record<string, unknown> \| null` | `null`                 | Model-specific options sent in the session update, such as `pronunciation_dict`. |

### Usage [#usage]

```ts title="tts.ts"
import { TTSUpdateSettingsFrame } from "@pipedog/core/frames/frames";
import { TogetherTTSService } from "@pipedog/together/tts";

const tts = new TogetherTTSService({
  apiKey: process.env.TOGETHER_API_KEY ?? "",
  settings: new TogetherTTSService.Settings({ voice: "af_heart" }),
});
```

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 TogetherTTSService.Settings({ voice: "af_bella" }),
});
```

### Event handlers [#event-handlers]

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

### Notes [#notes]

* Together sends 24 kHz audio. Any other `sampleRate` logs a warning.
* An interruption clears the text buffer (`input_text_buffer.clear`); the end of a turn commits it.
* Any settings change reconnects, since the session is configured in the connection URL.

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

* The WebSocket goes through the core `websocketConnect`. It works on Bun, Node, Deno and Cloudflare Workers.
* Tested against a local WebSocket fake, not against Together AI itself.