Text to Speech SDK

Generate natural-sounding speech from text with our SDKs. This guide will walk you through the essential steps to get started with text-to-speech synthesis in your applications.

Prerequisites

Before you begin, make sure you have:

• An aiOla API key (get one here)
• Python 3.10+ (for Python SDK) or Node.js 18+ (for TypeScript SDK)

Step 1: Install the SDK

$
pip install aiola

Step 2: Set up authentication

First, you’ll need to generate an access token using your API key:

1
from aiola import AiolaClient
2
3
# Generate access token
4
result = AiolaClient.grant_token(api_key='your-api-key')
5
access_token = result['accessToken']
6
7
# Create client
8
client = AiolaClient(access_token=access_token)

Step 3: Generate speech from text

Here’s how to convert text to speech and save it as an audio file:

1
# Generate speech from text
2
text = "Hello, this is a sample text to speech conversion using aiOla SDK."
3
4
audio = client.tts.synthesize(
5
    text=text,
6
    voice='tara',  # Choose from available voices
7
    language='en'
8
)
9
10
# Save the audio to a file
11
with open('output.wav', 'wb') as f:
12
    for chunk in audio:
13
        f.write(chunk)
14
15
print("Audio file generated successfully!")

Real-time streaming

For real-time audio streaming, check out our dedicated Text to Speech Streaming Guide which covers:

• Streaming audio generation for immediate playback
• Chunk-based processing for low latency
• Node.js implementations

Available voices

The following predefined voices are available: tara, zoe, zac, dan, jess, leo, mia, julia, and leah.

Supported language

The SDK currently supports:

• English (en) - Primary language for text-to-speech synthesis

Error handling

Always implement proper error handling for your API calls:

1
try:
2
    audio = client.tts.synthesize(
3
        text="Sample text for speech synthesis.",
4
        voice='jess',
5
        language='en'
6
    )
7
    
8
    with open("output.wav", "wb") as f:
9
        for chunk in audio:
10
            f.write(chunk)
11
        
12
    print("Speech synthesis completed successfully!")
13
    
14
except Exception as e:
15
    print(f"Speech synthesis failed: {e}")

Async operations (Python)

For asynchronous operations in Python:

1
from aiola import AsyncAiolaClient
2
import asyncio
3
4
async def async_tts_example():
5
    # Generate access token
6
    result = AsyncAiolaClient.grant_token(api_key='your-api-key')
7
    access_token = result['accessToken']
8
    
9
    # Create async client
10
    async_client = AsyncAiolaClient(access_token=access_token)
11
    
12
    # Generate speech asynchronously
13
    audio = await async_client.tts.synthesize(
14
        text="This is async text to speech.",
15
        voice='jess',
16
        language='en'
17
    )
18
    
19
    # Save audio
20
    with open("async_output.wav", "wb") as f:
21
        async for chunk in audio:
22
            f.write(chunk)
23
24
# Run the async function
25
asyncio.run(async_tts_example())

Best practices

1. Text Length: Keep text reasonably short for optimal performance
2. Error Handling: Always implement try-catch blocks for API calls
3. Resource Management: Properly handle audio streams and file operations
4. Audio Format Compatibility: Ensure audio format compatibility across different environments
5. Rate Limiting: Be mindful of API rate limits for production applications

Next steps

Now that you’ve successfully generated your first audio file, you can:

• Explore TTS Streaming for real-time speech synthesis
• Learn about Speech to Text SDK for converting speech back to text
• Check out the SDK repositories for more examples:
  • Python SDK
  • TypeScript SDK