Text-to-Speech API

Generate high-quality audio from text using Audian's text-to-speech service. Support for multiple languages and voice options.

Endpoint

POST https://api.audian.com:8443/v2/media/text-to-speech

Request

Headers

Content-Type: application/json
X-Auth-Token: YOUR_API_KEY

Parameters

Parameter	Type	Required	Description
text	String	Yes	Text to convert to speech (max 5000 characters)
voice	String	No	Voice ID (default: en-US-neural-1)
language	String	No	Language code (default: en-US)
speed	Number	No	Speech speed (0.5 - 2.0, default: 1.0)
pitch	Number	No	Voice pitch (-20 to 20, default: 0)
name	String	No	Name for the generated media file

Available Voices

English (US)

• en-US-neural-1 - Standard male voice
• en-US-neural-2 - Standard female voice
• en-US-neural-3 - Professional male voice
• en-US-neural-4 - Friendly female voice

English (UK)

• en-GB-neural-1 - Standard male voice
• en-GB-neural-2 - Standard female voice

Spanish

• es-ES-neural-1 - Standard male voice
• es-ES-neural-2 - Standard female voice

French

• fr-FR-neural-1 - Standard male voice
• fr-FR-neural-2 - Standard female voice

German

• de-DE-neural-1 - Standard male voice
• de-DE-neural-2 - Standard female voice

Examples

Basic Text-to-Speech

curl -X POST https://api.audian.com:8443/v2/media/text-to-speech \
  -H "X-Auth-Token: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Thank you for calling. Your call is important to us.",
    "voice": "en-US-neural-2",
    "language": "en-US",
    "name": "ivr-greeting"
  }'

JavaScript/Node.js

const axios = require('axios');

const generateSpeech = async () => {
  try {
    const response = await axios.post(
      'https://api.audian.com:8443/v2/media/text-to-speech',
      {
        text: 'Thank you for calling. Your call is important to us.',
        voice: 'en-US-neural-2',
        language: 'en-US',
        speed: 1.0,
        pitch: 0,
        name: 'ivr-greeting'
      },
      {
        headers: {
          'Authorization': 'Bearer YOUR_API_KEY',
          'Content-Type': 'application/json'
        }
      }
    );
    console.log('Speech generated:', response.data);
  } catch (error) {
    console.error('Generation failed:', error);
  }
};

generateSpeech();

Python

import requests
import json

def generate_speech(api_key, text, voice='en-US-neural-2', 
                   language='en-US', speed=1.0, pitch=0, name=None):
    url = 'https://api.audian.com:8443/v2/media/text-to-speech'
    headers = {
        'X-Auth-Token': api_key,
        'Content-Type': 'application/json'
    }
    
    payload = {
        'text': text,
        'voice': voice,
        'language': language,
        'speed': speed,
        'pitch': pitch
    }
    
    if name:
        payload['name'] = name
    
    response = requests.post(url, headers=headers, json=payload)
    return response.json()

# Usage
result = generate_speech(
    api_key='YOUR_API_KEY',
    text='Thank you for calling. Your call is important to us.',
    voice='en-US-neural-2',
    name='ivr-greeting'
)
print(result)

Advanced with Speed and Pitch

curl -X POST https://api.audian.com:8443/v2/media/text-to-speech \
  -H "X-Auth-Token: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Press 1 for sales, 2 for support, or 3 for billing",
    "voice": "en-US-neural-1",
    "language": "en-US",
    "speed": 1.1,
    "pitch": 2,
    "name": "ivr-menu-options"
  }'

Response

Success (200)

{
  "id": "media_tts_abc123",
  "name": "ivr-greeting",
  "text": "Thank you for calling. Your call is important to us.",
  "voice": "en-US-neural-2",
  "language": "en-US",
  "speed": 1.0,
  "pitch": 0,
  "url": "https://api.audian.com:8443/v2/media/media_tts_abc123",
  "duration": 3.2,
  "format": "wav",
  "size": 51200,
  "created_at": "2024-02-04T10:35:00Z"
}

Error (400)

{
  "error": "invalid_voice",
  "message": "The specified voice does not exist"
}

Parameters Guide

Speed

• Range: 0.5 to 2.0
• Default: 1.0
• 0.5: Half speed (slower speech)
• 1.0: Normal speed
• 2.0: Double speed (faster speech)

Pitch

• Range: -20 to 20
• Default: 0
• Negative values: Lower pitch (deeper voice)
• Positive values: Higher pitch (lighter voice)

Use Cases

Interactive Voice Response (IVR)

Generate dynamic menu prompts and information messages.

const menuText = `Press 1 for sales, 2 for support, or 3 for billing`;
// Generate and use in IVR system

Voicemail Greetings

Create professional voicemail prompts in multiple languages.

const greetingText = `You have reached our office. We are currently closed.`;
// Generate and assign to voicemail box

Notifications

Generate alert and notification messages.

const notificationText = `Your appointment reminder: You have a meeting today at 2 PM`;
// Generate and play to caller

Caching and Performance

Generated speech files are cached and reused when identical requests are made. This improves performance and reduces processing time for commonly used prompts.

Limits and Quotas

• Text limit: 5000 characters per request
• API calls: See your plan for TTS generation limits
• File retention: Generated files retained for 90 days
• Concurrent requests: Up to 10 concurrent TTS generations per API key