Getting Started

Use the Connector in Your Project

Application Requirements

Java Development Kit (JDK)

The application using the MuleSoft Vectors Connector must use MuleSoft Runtime >= 4.9.0 and Java Development Kit (JDK) 17.

Option 1: Maven Central Repository

(opens in a new tab)

<dependency>
    <groupId>io.github.mulesoft-ai-chain-project</groupId>
    <artifactId>mule4-whisperer-connector</artifactId>
    <version>{version}</version>
    <classifier>mule-plugin</classifier>
</dependency>

Option 2: Local Maven Repository

git clone https://github.com/MuleSoft-AI-Chain-Project/mule-whisperer-connector.git
cd mule-whisperer-connector

export MAVEN_OPTS="--add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.net=ALL-UNNAMED --add-opens=java.base/java.util.regex=ALL-UNNAMED --add-opens=java.base/java.lang.reflect=ALL-UNNAMED --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.xml/javax.xml.namespace=ALL-UNNAMED"

 
For Java 17
mvn clean install -Dmaven.test.skip=true -DskipTests -Dgpg.skip -Djdeps.multiRelease=17

<dependency>
    <groupId>com.mulesoft.connectors</groupId>
    <artifactId>mule4-whisperer-connector</artifactId>
    <version>{version}</version>
    <classifier>mule-plugin</classifier>
</dependency>

Connector Configuration

The configuration for the MuleSoft Whisperer connector is simple. Go to the Global Elements in your MuleSoft project and create a new configuration. In the Connector Configuration, you will find the MuleSoft Whisperer Configuration. Select it and press OK. You can choose between a cloud-based API setup or a local solution.

Whisperer JNI

Whisperer JNI (opens in a new tab) is a JNI wrapper for whisper.cpp, that allows transcribe speech to text in Java. Available models can be accessed via Whisper.cpp on Hugging Face (opens in a new tab).

Whisperer JNI (local .bin)

Reference model.bin locally

• Threads: Number of CPU threads allocated to the operation. The default value is 4.
• Translate: A boolean that indicates whether the input should be translated.
• Print progress: Boolean value to enable or disable the progress print.
• File path: The path to the Whisper model. When deploying the Mule application, place the model file (.bin) in the app.home directory. Use the relative path mule.home ++ "/apps/" ++ app.name ++ "/model.bin" to specify it.

Whisperer JNI (remote .bin)

Download model.bin on startup

• Threads: Number of CPU threads allocated to the operation. The default value is 4.
• Translate: A boolean that indicates whether the input should be translated.
• Print progress: Boolean value to enable or disable the progress print.
• Repository url: The URL of the repository where the Whisper model is stored.
• Installation file path: The path to the installation file.

OpenAI Whisperer

• Api key: The API key for the OpenAI service.
• Tls context: The TLS context for the OpenAI service.