Skip to navigation
Voice Cloning

Instant Voice Clone (Python SDK)

Clone a voice from a short audio sample using the Python SDK.
View as Markdown

Create an instant voice clone by uploading a short audio sample (5-15 seconds) via the Python SDK.

You can access the source code for the Python SDK on our GitHub repository.

Prefer plain HTTP? The Instant Voice Clone (REST API) page covers the same operation without the SDK.

Requirements

Before you begin, ensure you have the following:

  • Python (3.9 or higher) installed on your machine.
  • An API key from the Smallest AI platform.

Setup

Install our SDK

pip install smallestai

Set your API key as an environment variable.

export SMALLEST_API_KEY=YOUR_API_KEY

Add your Voice

The Smallest AI SDK allows you to clone your voice by uploading an audio file. This feature is available both synchronously and asynchronously, making it flexible for different use cases. Below are examples of how to use this functionality.

Synchronously

python
from smallestai import SmallestAI
def main():
    client = SmallestAI()  # reads SMALLEST_API_KEY from the environment
    with open("my_voice.wav", "rb") as f:
        res = client.waves.create_voice_clone(
            display_name="My Voice",
            file=("my_voice.wav", f, "audio/wav"),
        )
    print(res)
if __name__ == "__main__":
    main()

Asynchronously

python
import asyncio
from smallestai import AsyncSmallestAI
async def main():
    client = AsyncSmallestAI()  # reads SMALLEST_API_KEY from the environment
    with open("my_voice.wav", "rb") as f:
        res = await client.waves.create_voice_clone(
            display_name="My Voice",
            file=("my_voice.wav", f, "audio/wav"),
        )
    print(res)
if __name__ == "__main__":
    asyncio.run(main())

Parameters

  • api_key: Your API key. Set the SMALLEST_API_KEY environment variable, or pass it explicitly with SmallestAI(api_key="YOUR_API_KEY").
  • display_name: Name of the voice to be created.
  • file: The audio file to clone from, opened in binary mode.
  • Optional: description, accent, tags, language, and model.
  • Pass the file as a (filename, file_object, content_type) tuple so the upload carries the right file type.

These parameters are part of the create_voice_clone function. They can be set when calling the function as shown above.

Get All Cloned Voices

Once you have cloned your voices, you can retrieve a list of all cloned voices associated with your account using the following code:

python
from smallestai import SmallestAI
client = SmallestAI()  # reads SMALLEST_API_KEY from the environment
print(f"Available Voices: {client.waves.list_voice_clones()}")

If you have any questions or run into any issues, our community is here to help!