Text to Speech (Lightning)

Voices, Voice IDs, and Supported Languages

View as Markdown

Use this page to find your voice ID, list all voices available on each TTS model, and check the supported languages. Works via the REST API or Python SDK.

Lightning v3.1 — voices & languages reference

The Lightning v3.1 model card has the curated voice catalog, “Best Voices” tables per language, and the canonical supported-language list.

Pulse STT — supported languages

The Pulse STT model card has the language list and which features are supported per language.

The smallestai Python SDK is being updated. If the SDK example below doesn’t work, use the underlying REST API directly (see the API reference under Waves → API Reference). Streaming synthesis via WavesStreamingTTS is unaffected.

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.
  • The Smallest AI Python SDK installed. If you haven’t installed it yet, follow the instructions below:

Install the SDK

$pip install smallestai

Set your API key as an environment variable:

$export SMALLEST_API_KEY=YOUR_API_KEY

Fetch Available Voices, Models, and Languages

The Smallest AI SDK allows you to query the available languages, voices, and models for your TTS needs. Here’s how you can do it:

python
1from smallestai.waves import WavesClient
2
3def main():
4    client = WavesClient(api_key="YOUR_API_KEY")
5
6    # Get available languages
7    languages = client.get_languages()
8    print(f"Available Languages: {languages}")
9
10    # Get available voices for the "lightning-v3.1" model
11    voices = client.get_voices(model="lightning-v3.1")
12    print(f"Available Voices (Model: 'lightning-v3.1'): {voices}")
13
14    # Get user-specific cloned voices
15    cloned_voices = client.get_cloned_voices()
16    print(f"Available Cloned Voices: {cloned_voices}")
17
18    # Get available models
19    models = client.get_models()
20    print(f"Available Models: {models}")
21
22if __name__ == "__main__":
23    main()

Explanation of Functions

  • get_languages(): Retrieves the list of supported languages for Text-to-Speech.
  • get_voices(model="model_name"): Retrieves the voices available for a specific model (e.g., “lightning-v3.1”).
  • get_cloned_voices(): Fetches all user-specific cloned voices.
  • get_models(): Retrieves the TTS models on the platform available through API.

Need Help?

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