# AssemblyAI > Streaming text-to-speech with per-word timings over AssemblyAI's Streaming TTS WebSocket API. Source: https://polvallverdu.github.io/pipedog/docs/services/tts/assemblyai/ ## Overview [#overview] `AssemblyAITTSService` streams text to AssemblyAI's Streaming TTS WebSocket API over one session and plays the audio as it arrives, with per-word timings for word-level `TTSTextFrame`s. It is a port of Pipecat's `AssemblyAITTSService`. AssemblyAI's speech-to-text services, in the same package, are on the [AssemblyAI speech-to-text](https://polvallverdu.github.io/pipedog/docs/services/stt/assemblyai.md) page. Pipecat's documentation for the same service. `packages/assemblyai/src/tts.ts`. ## Installation [#installation] ```bash bun add @pipedog/assemblyai ``` ## Prerequisites [#prerequisites] * An [AssemblyAI](https://www.assemblyai.com) account and API key, passed as `apiKey` (the examples read `ASSEMBLYAI_API_KEY`). A temporary token opens a single session, so it can't carry the service's reconnects and session renewals. ## AssemblyAITTSService [#assemblyaittsservice] ### Configuration [#configuration] | Option | Type | Required | Description | |---|---|---|---| | `apiKey` | `string` | yes | AssemblyAI API key. A temporary token opens a single session, so it can't carry the service's reconnects and session renewals. | | `url` | `string \| undefined` | no | Streaming TTS WebSocket URL. Use `wss://tts.eu.assemblyai.com/v1/ws` to process text and audio in the EU. A cloned voice works only on the host of the zone it was created in. | | `sampleRate` | `number \| null \| undefined` | no | Output sample rate in Hz. If null, uses the pipeline's output rate. | | `settings` | `AssemblyAITTSSettings \| 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. | | `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. | The default URL is `wss://tts.us.assemblyai.com/v1/ws`. Use `wss://tts.eu.assemblyai.com/v1/ws` to process text and audio in the EU. A cloned voice works only on the host of the zone it was created in. ### Settings [#settings] Runtime-updatable settings, passed as `settings: new AssemblyAITTSService.Settings({...})` (`AssemblyAITTSSettings`). Settings you leave out keep their defaults. The session is configured when it connects, so changing any of them reconnects. | Setting | Type | Default | Description | | ---------- | ------------------ | ------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `voice` | `string \| null` | `"49c443a4-8a1d-5f7e-b70b-98bdbd9823c3"` (Audrey) | Sent as `voice_id`: any voice by its ID, an AssemblyAI voice by its library slug such as `aai-jane`, or a cloned voice by the slug the dashboard shows. `null` leaves the voice to the server. | | `language` | `Language \| null` | `null` | The language the session speaks: German, English, Spanish, French, Italian or Portuguese. Unset, the voice's own language. | | `model` | `string \| null` | `null` | The model, such as `assemblyai-tts-1`. Unset, the language's default model. | ### Usage [#usage] ```ts title="tts.ts" import { AssemblyAITTSService } from "@pipedog/assemblyai/tts"; import { TTSUpdateSettingsFrame } from "@pipedog/core/frames/frames"; import { Language } from "@pipedog/core/transcriptions/language"; // Speaks in Audrey, the default voice. const tts = new AssemblyAITTSService({ apiKey: process.env.ASSEMBLYAI_API_KEY ?? "" }); ``` Pick a voice and a region: ```ts // A library voice by its slug, processed in the EU. const eu = new AssemblyAITTSService({ apiKey: process.env.ASSEMBLYAI_API_KEY ?? "", url: "wss://tts.eu.assemblyai.com/v1/ws", settings: new AssemblyAITTSService.Settings({ voice: "aai-jane", language: Language.EN }), }); ``` Change settings mid-call with a `TTSUpdateSettingsFrame`: ```ts // The session is configured at connect time, so a new voice reconnects. const update = new TTSUpdateSettingsFrame({ delta: new AssemblyAITTSService.Settings({ voice: "987db62e-a2c2-569a-9c4d-82460cdea1bd" }), }); ``` ### Notes [#notes] * Each sentence is sent as its own request (a `Generate`, then a `Flush`). With `TextAggregationMode.TOKEN`, the turn's text streams as it is generated and is flushed when the turn ends. Text longer than the session's limit is split across `Generate` messages. * Interruptions send `Cancel`, which stops synthesis in flight and keeps the session open. * The service keeps an idle session open with a `KeepAlive` every 30 seconds, replaces a session between requests before its one-hour limit, and waits as long as an error asks before reconnecting. * `sampleRate` left out uses the pipeline's output rate. ## Runtimes [#runtimes] | 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/assemblyai/package.json`: ✅ means the compat smoke test passes on that runtime. The service uses the global `WebSocket` (through core's `websocketConnect`, which sends the `Authorization` header on the handshake on Cloudflare Workers too). No AssemblyAI SDK is needed.