Groq

OverviewCopy Anchor Link

• GroqTTSService: posts each sentence to Groq's /audio/speech endpoint and pushes the WAV it returns as audio frames.

InstallationCopy Anchor Link

bun add @pipedog/groq

import { GroqTTSService } from "@pipedog/groq/tts";

PrerequisitesCopy Anchor Link

• A Groq account and an API key from the Groq console.
• Pass the key as apiKey. The examples read it from GROQ_API_KEY.

GroqTTSServiceCopy Anchor Link

Posts to https://api.groq.com/openai/v1/audio/speech.

ConfigurationCopy Anchor Link

SettingsCopy Anchor Link

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

UsageCopy Anchor Link

import { TTSUpdateSettingsFrame } from "@pipedog/core/frames/frames";
import { GroqTTSService } from "@pipedog/groq/tts";

const tts = new GroqTTSService({
  apiKey: process.env.GROQ_API_KEY ?? "",
  settings: new GroqTTSService.Settings({ voice: "autumn" }),
});

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 GroqTTSService.Settings({ voice: "diana" }),
});

NotesCopy Anchor Link

• outputFormat is "wav" by default; the frames carry the WAV's own sample rate and channel count.
• A failed request produces an ErrorFrame instead of audio.

Runtime notesCopy Anchor Link

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

• Requests go through fetch (upstream uses the groq SDK). It works on Bun, Node, Deno and Cloudflare Workers.
• The whole response is read and parsed as one WAV. Upstream parses each streamed chunk as a WAV.
• The deprecated InputParams and the params, model_name and voice_id options are not ported. Use settings.
• Tested against a local fake, not against Groq itself.