Together AI

OverviewCopy Anchor Link

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

InstallationCopy Anchor Link

bun add @pipedog/together

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

PrerequisitesCopy Anchor Link

• A Together AI account and an API key from Together AI.
• Pass the key as apiKey. The examples read it from TOGETHER_API_KEY.

TogetherTTSServiceCopy Anchor Link

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

ConfigurationCopy Anchor Link

SettingsCopy Anchor Link

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

UsageCopy Anchor Link

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:

// 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 handlersCopy Anchor Link

NotesCopy Anchor Link

• 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 notesCopy Anchor Link

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.