Speech & Audio Applications

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

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

// 1. Speech-to-text
const transcript = await client.audio.transcriptions.create({
  model: "whisper-v3-turbo",
  file: fs.createReadStream("./sample.wav"),
});
console.log(transcript.text);

// 2. Audio understanding: a multipart upload to /v1/audio/understand, not a chat call
const form = new FormData();
form.append("file", new Blob([fs.readFileSync("./sample.wav")]), "sample.wav");
form.append("question", "Summarize tone, background audio, and key events in one short paragraph.");
form.append("model", "gemini-3-flash-audio");

const res = await fetch("https://api.kymaapi.com/v1/audio/understand", {
  method: "POST",
  headers: { Authorization: `Bearer ${process.env.KYMA_API_KEY}` },
  body: form,
});
const { answer } = await res.json();

// 3. Text-to-speech (needs a funded balance)
const spoken = await client.audio.speech.create({
  model: "minimax-speech-turbo",
  voice: "female-shaonv", // or any voice from GET /v1/audio/voices
  input: answer,
  response_format: "mp3",
});

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