Speak Install & Auth

Overview

Set up Speak Language Learning SDK/API and configure authentication credentials for AI-powered language tutoring integration.

Prerequisites

• Node.js 18+ or Python 3.10+
• Package manager (npm, pnpm, or pip)
• Speak developer account with API access
• API key from Speak developer dashboard

Instructions

Step 1: Install SDK

# Node.js
npm install @speak/language-sdk

# Python
pip install speak-language-sdk

# Alternative: Using OpenAI-compatible API
npm install openai  # Speak uses OpenAI's real-time API

Step 2: Configure Authentication

# Set environment variable
export SPEAK_API_KEY="your-api-key"
export SPEAK_APP_ID="your-app-id"

# Or create .env file
echo 'SPEAK_API_KEY=your-api-key' >> .env
echo 'SPEAK_APP_ID=your-app-id' >> .env

Step 3: Initialize Client

// src/speak/client.ts
import { SpeakClient } from '@speak/language-sdk';

const client = new SpeakClient({
  apiKey: process.env.SPEAK_API_KEY!,
  appId: process.env.SPEAK_APP_ID!,
  language: 'ko', // Target language: Korean, Spanish (es), Japanese (ja), etc.
});

Step 4: Verify Connection

async function verifyConnection() {
  try {
    const status = await client.health.check();
    console.log('Speak connection verified:', status);
    return true;
  } catch (error) {
    console.error('Connection failed:', error);
    return false;
  }
}

Supported Languages

Output

• Installed SDK package in node_modules or site-packages
• Environment variable or .env file with API credentials
• Successful connection verification output

Error Handling

Examples

TypeScript Setup with Speech Recognition

import { SpeakClient, SpeechRecognizer } from '@speak/language-sdk';

const client = new SpeakClient({
  apiKey: process.env.SPEAK_API_KEY!,
  appId: process.env.SPEAK_APP_ID!,
  language: 'es',
});

const recognizer = new SpeechRecognizer(client, {
  onSpeechResult: (result) => {
    console.log('User said:', result.transcript);
    console.log('Pronunciation score:', result.pronunciationScore);
  },
  onError: (error) => console.error('Speech error:', error),
});

Python Setup

import os
from speak_sdk import SpeakClient, LessonSession

client = SpeakClient(
    api_key=os.environ.get('SPEAK_API_KEY'),
    app_id=os.environ.get('SPEAK_APP_ID'),
    language='ja'  # Japanese
)

# Verify connection
status = client.health.check()
print(f"Connected: {status.healthy}")

Resources

• Speak Developer Documentation
• Speak API Reference
• Speak Status Page
• OpenAI Real-time API (used by Speak)

Next Steps

After successful auth, proceed to speak-hello-world for your first lesson session.