شروع به کار با هوش مصنوعی Microsoft

// npm install openai dotenv
require("dotenv").config();

const fs = require("fs");
const OpenAI = require("openai");

const client = new OpenAI({
apiKey: process.env.LIARA_API_KEY,
baseURL: process.env.BASE_URL,
});

async function main() {
const response = await client.audio.speech.create({
  model: process.env.TTS_MODEL_NAME,
  voice: process.env.TTS_VOICE,
  input: "Hello! This audio was generated using Microsoft MAI Voice through Liara.",
  response_format: "mp3",
});

const buffer = Buffer.from(await response.arrayBuffer());

fs.writeFileSync("speech.mp3", buffer);

console.log("Audio saved to speech.mp3");
}

main().catch(console.error);

// npm install openai dotenv

require("dotenv").config();

const fs = require("fs");
const path = require("path");
const OpenAI = require("openai");
const { toFile } = require("openai");

const client = new OpenAI({
apiKey: process.env.LIARA_API_KEY,
baseURL: process.env.BASE_URL,
});

async function main() {
const audioPath = path.resolve(process.env.AUDIO_FILE);

if (!fs.existsSync(audioPath)) {
  throw new Error(`Audio file not found: ${audioPath}`);
}

const extension = path.extname(audioPath).toLowerCase();

const mimeTypes = {
  ".mp3": "audio/mpeg",
  ".wav": "audio/wav",
  ".flac": "audio/flac",
  ".m4a": "audio/mp4",
  ".ogg": "audio/ogg",
  ".webm": "audio/webm",
  ".aac": "audio/aac",
};

const mimeType = mimeTypes[extension];

if (!mimeType) {
  throw new Error(`Unsupported audio format: ${extension}`);
}

const audioBuffer = fs.readFileSync(audioPath);

const audioFile = await toFile(
  audioBuffer,
  path.basename(audioPath),
  {
    type: mimeType,
  }
);

const transcription = await client.audio.transcriptions.create({
  model: process.env.STT_MODEL_NAME,
  file: audioFile,
});

console.log(transcription.text);
}

main().catch(console.error);