Cartesia STT
Streaming speech-to-text using Cartesia’sink-whisper model. Uses ws, no vendor SDK required.
Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Streaming speech-to-text via Cartesia’s ink-whisper model.
ink-whisper model. Uses ws, no vendor SDK required.
npm install getpatter
import { CartesiaSTT } from "getpatter";
const stt = new CartesiaSTT(); // reads CARTESIA_API_KEY
const stt2 = new CartesiaSTT({ apiKey: "csk_...", language: "en" });
// npx tsx example.ts
import { Patter, Twilio, CartesiaSTT, ElevenLabsTTS } from "getpatter";
const phone = new Patter({ carrier: new Twilio(), phoneNumber: "+15550001234" });
const agent = phone.agent({
stt: new CartesiaSTT(), // CARTESIA_API_KEY from env
tts: new ElevenLabsTTS({ voiceId: "rachel" }),
systemPrompt: "You are a helpful assistant.",
});
await phone.serve({ agent });
