For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
DocumentationAPI ReferenceClient LibrariesChangelog
DocumentationAPI ReferenceClient LibrariesChangelog
  • Introduction
    • Introduction
  • Getting Started
    • Quickstart
    • Models
    • Authentication
    • HTTP Streaming
  • Text to Speech
    • How to TTS
    • LLM to TTS
    • Voice Models & Languages
  • Voice Cloning
    • Types of Cloning
    • Voice Clone via UI
    • How to Voice Clone
    • Delete Cloned Voice
    • Professional Voice Cloning
  • Integrations
    • LiveKit
    • Plivo
    • Vonage
  • Product
    • Projects
  • Best Practices
    • Voice Cloning Best Practices
    • PVC Best Practices
    • TTS Best Practices
LogoLogo
Voice AgentsModels
Voice AgentsModels
On this page
  • Step 1: Sign Up & get the API Key
  • Step 2: Install the SDK
  • Step 3: Make Your First API Call
  • Step 4: Explore More Features
  • Need Help?
Getting Started

Quickstart

||View as Markdown|
Was this page helpful?
Previous

Introduction

Next

Models

Built with

Step 1: Sign Up & get the API Key

  1. Visit platform and sign up for an account or log in if you already have an account.
  2. Navigate to API Key tab in your account dashboard.
  3. Create a new API Key and copy it.
  4. Export the API Key in your environment with the name SMALLEST_API_KEY, ensuring that your application can access it securely for authentication.

Step 2: Install the SDK

To install the latest version available

$pip install smallestai

When using an SDK in your application, make sure to pin to at least the major version (e.g., ==1.*). This helps ensure your application remains stable and avoids potential issues from breaking changes in future updates.

Step 3: Make Your First API Call

Here is a basic example of how to use the Python SDK to convert text to speech:

If you are using a voice_id corresponding to a voice clone, you should explicitly set the model parameter to "lightning-large" in the Smallest client or payload.

python
1from smallestai.waves import WavesClient
2
3def main():
4 client = WavesClient(api_key="YOUR_API_KEY")
5 client.synthesize(
6 "Modern problems require modern solutions.",
7 sample_rate=24000,
8 speed=1.0,
9 save_as="output.wav"
10 )
11
12if __name__ == "__main__":
13 main()

Replace YOUR_API_KEY with the API key you obtained in Step 2.

Step 4: Explore More Features

  • Voice Cloning: Create custom voice profiles by uploading voice samples.
  • Advanced Configurations: Customize speech synthesis with different voices, speeds, and sample rates.

For detailed documentation on all available features and endpoints, visit our API Reference.

Need Help?

If you have any questions or need assistance, please contact our support team at support@smallest.ai.