Getting Started with Uberduck API

This guide will help you make your first API request to Uberduck's text-to-speech service.

Prerequisites

Before you begin, you'll need:

1. An Uberduck account
2. An API key from your Uberduck dashboard
3. Basic knowledge of REST APIs and your preferred programming language

Step 1: Obtain an API Key

1. Sign in to your account at uberduck.ai
2. Navigate to your account settings
3. Select the API section
4. Generate a new API key
5. Copy your API key for use in requests

Step 2: Make Your First API Request

Let's create a simple text-to-speech request using one of Uberduck's pre-built voices.

Using cURL

curl -X POST https://api.uberduck.ai/v1/text-to-speech \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello world! This is my first Uberduck API request.",
    "voice": "polly_joanna",
    "model": "polly_neural"
  }'

Using JavaScript/Node.js

async function generateSpeech() {
  const response = await fetch('https://api.uberduck.ai/v1/text-to-speech', {
    method: 'POST',
    headers: {
      'Authorization': 'Bearer YOUR_API_KEY',
      'Content-Type': 'application/json'
    },
    body: JSON.stringify({
      text: 'Hello world! This is my first Uberduck API request.',
      voice: 'polly_joanna',
      model: 'polly_neural'
    })
  });

  const data = await response.json();
  console.log(`Speech generated! Audio available at: ${data.audio_url}`);
  
  // Play the audio (in browser environments)
  const audio = new Audio(data.audio_url);
  audio.play();
}

generateSpeech();

Using Python

import requests

url = "https://api.uberduck.ai/v1/text-to-speech"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}
payload = {
    "text": "Hello world! This is my first Uberduck API request.",
    "voice": "polly_joanna",
    "model": "polly_neural"
}

response = requests.post(url, json=payload, headers=headers)
data = response.json()

print(f"Speech generated! Audio available at: {data['audio_url']}")

Step 3: Explore Available Voices

Now that you've created your first text-to-speech request, you might want to explore the available voices.

curl -X GET "https://api.uberduck.ai/v1/voices?limit=10" \
  -H "Authorization: Bearer YOUR_API_KEY"

This will return the first 10 available voices. You can use various filter parameters to narrow down your search:

# Get English female voices
curl -X GET "https://api.uberduck.ai/v1/voices?language=english&gender=female&limit=10" \
  -H "Authorization: Bearer YOUR_API_KEY"

Step 4: Explore Available Models

You can also explore the available TTS models:

curl -X GET "https://api.uberduck.ai/v1/models" \
  -H "Authorization: Bearer YOUR_API_KEY"

Step 5: Customizing Your Request

For more advanced text-to-speech generation, you can customize your request with additional parameters:

// JavaScript example with extended parameters
const response = await fetch('https://api.uberduck.ai/v1/text-to-speech', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    text: 'This is a customized text-to-speech request with adjusted speed and pitch.',
    voice: 'polly_joanna',
    model: 'polly_neural',
    extended: {
      speed: 1.2,
      pitch: 0.5
    },
    output_format: 'mp3'
  })
});

Next Steps

Now that you've made your first API request, you can:

1. Explore more voice options
2. Learn about advanced parameters
3. Check out best practices
4. Integrate the API into your application

Troubleshooting

If you encounter any issues:

• Ensure your API key is valid and correctly formatted in the Authorization header
• Check that your request payload is valid JSON
• Verify that the voice and model you're using are compatible
• If you receive a rate limit error, wait before making another request
• For persistent issues, contact support@uberduck.ai