Node.js Integration

Learn how to integrate SM-AI-MODELS APIs into your Node.js applications.

Installation

Code
 
npm install node-fetch form-data

Text-to-Speech

Code
 
const fs = require('fs');

async function generateSpeech(text, voice = 'Yara', format = 'mp3') {
  const response = await fetch('http://localhost:9999/v1/audio/speech', {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify({
      input: text,
      voice: voice,
      response_format: format
    })
  });
  
  if (!response.ok) {
    throw new Error(`HTTP error: ${response.status}`);
  }
  
  return response.arrayBuffer();
}

// Example usage
async function main() {
  const audio = await generateSpeech('مرحباً بكم', 'Yara');
  fs.writeFileSync('output.mp3', Buffer.from(audio));
  console.log('Audio saved to output.mp3');
}

main();

Speech Recognition

Code
 
const fs = require('fs');
const FormData = require('form-data');

async function transcribeAudio(filePath) {
  const form = new FormData();
  form.append('file', fs.createReadStream(filePath));
  
  const response = await fetch('http://localhost:8088/v1/audio/transcriptions', {
    method: 'POST',
    body: form
  });
  
  if (!response.ok) {
    throw new Error(`HTTP error: ${response.status}`);
  }
  
  const data = await response.json();
  return data.text;
}

// Example usage
async function main() {
  const text = await transcribeAudio('recording.wav');
  console.log(`Transcribed: ${text}`);
}

main();

ES Modules Version

Code
 
import fs from 'fs/promises';
import { createReadStream } from 'fs';

// TTS
export async function speak(text, options = {}) {
  const { voice = 'Yara', format = 'mp3', speed = 1.0 } = options;
  
  const response = await fetch('http://localhost:9999/v1/audio/speech', {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify({
      input: text,
      voice,
      response_format: format,
      speed
    })
  });
  
  if (!response.ok) {
    const error = await response.json();
    throw new Error(error.error?.message || 'TTS failed');
  }
  
  return Buffer.from(await response.arrayBuffer());
}

// ASR
export async function transcribe(filePath) {
  const FormData = (await import('form-data')).default;
  const form = new FormData();
  form.append('file', createReadStream(filePath));
  
  const response = await fetch('http://localhost:8088/v1/audio/transcriptions', {
    method: 'POST',
    body: form
  });
  
  if (!response.ok) {
    const error = await response.json();
    throw new Error(error.error?.message || 'Transcription failed');
  }
  
  const data = await response.json();
  return data.text;
}

// Usage
const audio = await speak('مرحباً بكم', { voice: 'Yara' });
await fs.writeFile('greeting.mp3', audio);

const text = await transcribe('greeting.mp3');
console.log(text);

TypeScript

Code
 
interface SpeechOptions {
  voice?: 'Yara' | 'Nouf' | 'Yara_en';
  format?: 'mp3' | 'wav' | 'opus' | 'flac';
  speed?: number;
}

interface TranscriptionResponse {
  text: string;
}

async function generateSpeech(
  text: string, 
  options: SpeechOptions = {}
): Promise<Buffer> {
  const { voice = 'Yara', format = 'mp3', speed = 1.0 } = options;
  
  const response = await fetch('http://localhost:9999/v1/audio/speech', {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify({
      input: text,
      voice,
      response_format: format,
      speed
    })
  });
  
  if (!response.ok) {
    throw new Error(`HTTP ${response.status}`);
  }
  
  return Buffer.from(await response.arrayBuffer());
}

async function transcribeAudio(filePath: string): Promise<string> {
  const FormData = require('form-data');
  const fs = require('fs');
  
  const form = new FormData();
  form.append('file', fs.createReadStream(filePath));
  
  const response = await fetch('http://localhost:8088/v1/audio/transcriptions', {
    method: 'POST',
    body: form
  });
  
  if (!response.ok) {
    throw new Error(`HTTP ${response.status}`);
  }
  
  const data: TranscriptionResponse = await response.json();
  return data.text;
}

Express.js Integration

Code
 
const express = require('express');
const app = express();

app.use(express.json());

// TTS proxy endpoint
app.post('/api/speak', async (req, res) => {
  try {
    const { text, voice = 'Yara', format = 'mp3' } = req.body;
    
    const response = await fetch('http://localhost:9999/v1/audio/speech', {
      method: 'POST',
      headers: { 'Content-Type': 'application/json' },
      body: JSON.stringify({
        input: text,
        voice,
        response_format: format
      })
    });
    
    if (!response.ok) {
      return res.status(response.status).json(await response.json());
    }
    
    const contentType = format === 'mp3' ? 'audio/mpeg' : `audio/${format}`;
    res.setHeader('Content-Type', contentType);
    
    const buffer = Buffer.from(await response.arrayBuffer());
    res.send(buffer);
  } catch (error) {
    res.status(500).json({ error: error.message });
  }
});

app.listen(3000, () => {
  console.log('Server running on port 3000');
});