Speech & Audio Applications

import OpenAI from "openai";
import fs from "node:fs";

const client = new OpenAI({
  baseURL: "https://kymaapi.com/v1",
  apiKey: process.env.KYMA_API_KEY,
});

const audio = fs.createReadStream("./sample.wav");

const transcript = await client.audio.transcriptions.create({
  model: "whisper-v3-turbo",
  file: audio,
});

const understanding = await client.chat.completions.create({
  model: "gemini-3-flash-audio",
  messages: [
    { role: "system", content: "Summarize tone, background audio, and key events in one short paragraph." },
    { role: "user", content: transcript.text },
  ],
});

const spoken = await client.audio.speech.create({
  model: "minimax-speech-turbo",
  voice_id: "charlie",
  input: understanding.choices[0].message.content ?? "",
  response_format: "mp3",
});

fs.writeFileSync("./audio-summary.mp3", Buffer.from(await spoken.arrayBuffer()));