Leopard Speech-to-Text
Rust Quick Start

Platforms

• Linux (x86_64)
• macOS (x86_64, arm64)
• Windows (x86_64)
• NVIDIA Jetson Nano
• Raspberry Pi (3, 4)

Requirements

• Picovoice Account & AccessKey
• Rust 1.54+
• Cargo

Picovoice Account & AccessKey

Signup or Login to Picovoice Console to get your AccessKey. Make sure to keep your AccessKey secret.

Quick Start

Setup

1. Download and install Rust.

2. Add pv_leopard to the Cargo.toml manifest:

[dependencies]
pv_leopard = "*"

Usage

Create an instance of the engine:

use leopard::LeopardBuilder;

let access_key = "${ACCESS_KEY}"; // AccessKey obtained from Picovoice Console (https://console.picovoice.ai/)

let leopard: Leopard = LeopardBuilder::new()
    .access_key(access_key)
    .init()
    .expect("Unable to create Leopard");

Transcribe an audio file:

if let Ok(leopard_transcript) = leopard.process_file("${AUDIO_PATH}") {
    println!("{}", leopard_transcript.transcript);
}

Demo

For the Leopard Rust SDK, we offer demo applications that demonstrate how to use the Speech-to-Text engine on audio files.

Setup

Clone the Leopard repository from GitHub using HTTPS:

git clone --recurse-submodules https://github.com/Picovoice/leopard.git

Usage

Use the --help flag to see the usage options for the demo:

leopard/demo/rust/filedemo
cargo run --release -- --help

Run the following command to transcribe an audio file:

cargo run --release -- --access_key ${ACCESS_KEY} --input_audio_path ${AUDIO_PATH}

For more information on our Leopard demos for Rust, head over to our GitHub repository.

Resources