AI Models
Audixa AI offers two powerful text-to-speech models to suit different needs: Base and Advance. Each model is optimized for a different set of use cases, from general-purpose narration to highly expressive, custom voice generation.
Understanding the differences will help you choose the best model for your application.
Base Model
The Base model is the perfect choice for a wide range of applications. It is designed for reliability, speed, and high-quality audio output across a large and diverse voice library.
- Extensive Voice Library: Comes with 54 preset voices spanning various accents, genders, and styles.
- High Quality: Delivers clear, natural-sounding speech suitable for narration, content creation, and accessibility.
- Simplicity: Easy to use with straightforward API parameters.
For the majority of users, the Base model provides more than enough variety and quality to build incredible audio experiences.
Advance Model
The Advance model is built for users who require the highest level of customization, expressiveness, and unique vocal identity. While it has a smaller library of preset voices, its power lies in its advance features.
- Voice Cloning: Create a digital replica of any voice from a short audio sample.
- Custom Voices: Design unique, high-quality synthetic voices tailored to your brand or project.
- Superior Expressiveness: The model is fine-tuned for more nuanced and emotionally resonant speech.
- Greater Customization: Offers more detailed control over the final audio output.
The Advance model is ideal for enterprises, creators, and developers who need a signature voice or the flexibility of voice cloning.
Side-by-Side Comparison
| Feature | Base Model | Advance Model |
|---|---|---|
| Preset Voices | ✅ 54 Voices | ⚪️ Fewer (Focus is on custom voices) |
| Voice Cloning | ❌ Not Supported | ✅ Supported |
| Custom Voices | ❌ Not Supported | ✅ Supported |
| Expressiveness | High Quality & Natural | Highest Quality & More Nuanced |
| Best For | General applications, large selection | Branding, custom experiences, unique vocal identity |
API model Parameter | "base" | "advance" |
Specifying a Model in Your API Request
To use a specific model, simply set the model parameter in the body of your POST request to the /tts endpoint.
- Using the Base Model
- Using the Advance Model
{
"text": "Hello, this is a voice from the Base model.",
"voice": "am_Ethan",
"model": "base"
}
{
"text": "This voice is generated by the more expressive Advance model.",
"voice": "custom_voice_id_123", // Example custom voice ID
"model": "advance"
}