Cheetah Speech-to-Text
Java Quick Start

Platforms

• Linux (x86_64)
• macOS (x86_64, arm64)
• Windows (x86_64)
• Raspberry Pi (3, 4, 5)

Requirements

• Picovoice Account and AccessKey
• Java 11+

Picovoice Account & AccessKey

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

Quick Start

Setup

1. Install JDK 11+.

2. Install the Java binding from the Maven Central Repository at:

ai.picovoice:cheetah-java:${version}

Usage

Create an instance of the engine with the Cheetah Streaming Speech-to-Text Builder class:

import ai.picovoice.cheetah.*;

final String accessKey = "${ACCESS_KEY}"; // AccessKey provided by Picovoice Console (https://console.picovoice.ai/)

try {
    Cheetah cheetah = new Cheetah.Builder()
        .setAccessKey(accessKey).build();
} catch (CheetahException ex) { }

Transcribe audio:

short[] getNextAudioFrame() {
    // .. get audioFrame
    return audioFrame;
}

String transcript = "";

while true {
    CheetahTranscript transcriptObj = cheetah.process(getNextAudioFrame());
    transcript += transcriptObj.getTranscript();

    if (transcriptObj.getIsEndpoint()) {
        CheetahTranscript finalTranscriptObj = cheetah.flush();
        transcript += finalTranscriptObj.getTranscript();
    }
}

When done resources have to be released explicitly:

cheetah.delete();

Model File

The Cheetah Speech-to-Text Java SDK comes preloaded with a default English language model (.pv file). Default models for other supported languages can be found in the Cheetah Speech-to-Text GitHub repository.

Create custom language models using the Picovoice Console. Here you can train language models with custom vocabulary and boost words in the existing vocabulary.

Pass in the .pv file via the .setModelPath() Builder argument:

Cheetah cheetah = new Cheetah.Builder()
        .setAccessKey("${ACCESS_KEY}")
        .setModelPath("${MODEL_PATH")
        .build();

Demo

For the Cheetah Streaming Speech-to-Text Java SDK, we offer demo applications that demonstrate how to use the Speech-to-Text engine on real-time audio streams (i.e. microphone input).

Setup

1. Clone the Cheetah Streaming Speech-to-Text repository from GitHub using HTTPS:

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

2. Build the Cheetah Streaming Speech-to-Text Java demo using Gradle:

cd cheetah/demo/java
./gradlew build

Usage

To see the usage options for the demos, use the -h flag:

java -jar build/libs/cheetah-mic-demo.jar -h

Ensure you have a working microphone connected to your system and run the following command to perform live speech-to-text:

java -jar build/libs/cheetah-mic-demo.jar -a ${ACCESS_KEY}

For more information on our Cheetah Streaming Speech-to-Text demos for Java, head over to our GitHub repository.

Resources