voice agents

caller audio ──▶ geko.stt.stream ──▶ your LLM ──▶ geko.tts.stream ──▶ caller hears it

import { Geko } from "@gekoai/sdk";

const geko = new Geko({ apiKey: process.env.GEKO_API_KEY });

async function listen(callAudio: AsyncIterable<Buffer>, onTurn: (text: string) => void) {
  // 200ms: a final ~0.4s after the caller stops. Raise it for slow, deliberate speakers.
  const stream = await geko.stt.stream({ endOfUtteranceMs: 200 });

  (async () => {
    for await (const frame of callAudio) stream.send(frame); // PCM16-LE mono 16 kHz
    stream.stop();
  })();

  for await (const event of stream) {
    if (event.type === "final") onTurn(event.text); // the server decided the turn ended
  }
}

// Split an incoming text stream on sentence boundaries so we synthesize
// a natural unit at a time instead of one word at a time.
async function* sentences(chunks: AsyncIterable<string>) {
  let buf = "";
  for await (const piece of chunks) {
    buf += piece;
    let m: RegExpMatchArray | null;
    // flush each completed sentence as it appears
    while ((m = buf.match(/[^.!?…]*[.!?…]+\s*/))) {
      yield m[0].trim();
      buf = buf.slice(m[0].length);
    }
  }
  if (buf.trim()) yield buf.trim(); // trailing text with no terminator
}

// `llmText` is whatever your model gives you as it streams — an async
// iterable of text deltas. Geko speaks each sentence as it's ready.
export async function* speak(
  llmText: AsyncIterable<string>,
  signal?: AbortSignal,
) {
  for await (const sentence of sentences(llmText)) {
    for await (const wav of geko.tts.stream({
      text: sentence,
      voice: "Aigerim",
      nfe: 16, // interactive: favor speed
      signal, // let the caller cut synthesis short on barge-in
    })) {
      yield wav; // hand this WAV chunk to your audio output
    }
  }
}

const controller = new AbortController();

async function handleTurn(turnAudio: Buffer) {
  const { text } = await hear(turnAudio);   // geko: caller audio → text
  const llmTextStream = yourModel(text);    // yours: text → streamed reply
  for await (const wav of speak(llmTextStream, controller.signal)) {
    playToCaller(wav);                      // geko: reply text → audio
  }
}

// caller starts talking over the agent (barge-in) → stop speaking:
// controller.abort();