Rust API Reference

ModelType Enum

The ModelType enum defines the AI models available in the Revoize SDK:

#[derive(Debug)]
pub enum ModelType {
    /// Capella: A lightweight model optimized for efficiency.
    Capella,
    /// Algol: A generative model with advanced capabilities.
    Algol,
}

init Function

Signature

pub fn init(model_type: ModelType) -> Result<(), Box<dyn Error>>

The init function is your starting point for using the Revoize SDK. It sets up the SDK with the specified model type. Note: Make sure to call this function before any other SDK functions to ensure everything is properly set up.

Parameters

• model_type The model type to initialize the SDK with. Choose from the ModelType enum variants (e.g., ModelType::Capella or ModelType::Algol).

Returns

A Result indicating success or failure:

• Ok(()) if initialization is successful.
• Err if an error occurs during initialization (e.g., session creation, state setup, or missing model constants).

Errors

An error is returned if initialization fails at any step.

Example

use revoize_sdk::init;
use revoize_sdk::ModelType;

fn main() {
    // Initialize the SDK with the Capella model.
    init(ModelType::Capella).expect("Failed to initialize Revoize SDK");
}

process Function

Signature

pub fn process(audio_chunk: &[f32]) -> Result<Vec<f32>, Box<dyn Error>>

The process function takes an input audio chunk and returns the enhanced chunk.

WARNING

• Ensure init() is called before using this function.
• The audio_chunk should be from a 48 kHz recording.

Parameters

• audio_chunk A slice of f32 representing single-channel audio samples from a 48 kHz recording.

Returns

• Result<Vec<f32>, Box<dyn std::error::Error>> On success, returns a vector of enhanced audio samples. Otherwise, returns an error if processing fails (e.g., if the SDK hasn't been initialized).

Example

use revoize_sdk::{init, process};
use revoize_sdk::ModelType;

fn main() -> Result<(), Box<dyn std::error::Error>> {
    // Initialize the SDK before processing audio.
    init(ModelType::Capella)?;

    // Prepare an audio chunk from a 48 kHz recording.
    let audio_chunk = vec![1.0_f32; 480 * 10]; // 10 frames of 480 samples each
    let enhanced_audio = process(&audio_chunk)?;

    println!("Enhanced audio has {} samples", enhanced_audio.len());
    Ok(())
}