@pipedog/speechify

Speechify text-to-speech for pipedog: SpeechifyHttpTTSService, which streams audio and word timestamps over server-sent events with fetch.

A port of Pipecat's pipecat.services.speechify. Subpaths mirror upstream: @pipedog/speechify/tts.

Install

bun add @pipedog/core @pipedog/asyncio @pipedog/speechify

No peer dependencies.

Usage

import { SpeechifyHttpTTSService } from "@pipedog/speechify/tts";

const tts = new SpeechifyHttpTTSService({
  apiKey: process.env.SPEECHIFY_API_KEY ?? "",
  settings: new SpeechifyHttpTTSService.Settings({ model: "simba-3.2", voice: "geffen_32" }),
});
// new Pipeline([transport.input(), stt, userAggregator, llm, tts, transport.output(), ...])

Pass fetch to use your own HTTP client; it stands in for upstream's shared aiohttp session.

Runtimes

Bun, Node.js 22+, Deno and Cloudflare Workers.

Links

• Docs: Speechify, voice bot guide
• pipedog README
• License: BSD 2-Clause, a port of Pipecat (Copyright (c) 2024–2026 Daily). See LICENSE.