Speechify

OverviewCopy Anchor Link

SpeechifyHttpTTSService posts each sentence to Speechify's /v1/audio/stream/with-timestamps endpoint and reads the Server-Sent Events it answers with: PCM audio chunks and word-level speech marks. The marks become word timestamps, so the bot's TTSTextFrames follow the audio.

InstallationCopy Anchor Link

bun add @pipedog/speechify

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

PrerequisitesCopy Anchor Link

• A Speechify API account and an API key.
• Pass the key as apiKey. The examples read it from SPEECHIFY_API_KEY.

ConfigurationCopy Anchor Link

SettingsCopy Anchor Link

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

UsageCopy Anchor Link

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

const tts = new SpeechifyHttpTTSService({
  apiKey: process.env.SPEECHIFY_API_KEY ?? "",
  settings: new SpeechifyHttpTTSService.Settings({
    model: "simba-3.5",
    voice: "geffen_32",
    textNormalization: true,
  }),
});

Change settings mid-call with a TTSUpdateSettingsFrame:

// Queue it on the worker, or push it from a processor upstream of the service.
const update = new TTSUpdateSettingsFrame({
  delta: new SpeechifyHttpTTSService.Settings({ voice: "another-voice-id" }),
});

NotesCopy Anchor Link

• The sample rate must be one of Speechify's PCM rates (8000, 16000, 22050, 24000, 44100 or 48000). For any other pipeline rate the service asks for 24000 Hz, tags its audio frames with that rate, and the output transport resamples.
• Requests pin Speechify's API version (Speechify-Version: 2026-09-30), and send Speechify-Caller: pipecat with the pipedog version.
• Speechify marks the pieces of a hyphenated word separately. The service joins marks that touch in the text, so text-to-speech is one word timestamp.
• A mid-stream speech.error event is reported as an error frame. A non-200 response is too.

Runtime notesCopy Anchor Link

• It uses the global fetch and reads the response as a stream, so it works on Bun, Node, Deno and Cloudflare Workers. Pass fetch to use another one (upstream takes an aiohttp session).
• Tested against a local server that replays Speechify's event format, as upstream's tests do for the parsing, not against Speechify itself.

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