Async

OverviewCopy Anchor Link

• 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.

InstallationCopy Anchor Link

bun add @pipedog/asyncai

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

PrerequisitesCopy Anchor Link

• 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.

AsyncAITTSServiceCopy Anchor Link

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

ConfigurationCopy Anchor Link

SettingsCopy Anchor Link

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.

UsageCopy Anchor Link

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:

// 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 handlersCopy Anchor Link

AsyncAIHttpTTSServiceCopy Anchor Link

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

ConfigurationCopy Anchor Link

It takes the same settings as the WebSocket service.

UsageCopy Anchor Link

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

NotesCopy Anchor Link

• 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 notesCopy Anchor Link

• 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.

Generated from pipecat.runtimes and pipecat.compat in packages/asyncai/package.json: ✅ means the compat smoke test passes on that runtime.