Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/ballerina-platform/module-ballerinax-openai.audio
https://github.com/ballerina-platform/module-ballerinax-openai.audio
ai audio ballerina openai whisper
Last synced: about 1 month ago
JSON representation
- Host: GitHub
- URL: https://github.com/ballerina-platform/module-ballerinax-openai.audio
- Owner: ballerina-platform
- License: apache-2.0
- Created: 2024-08-06T06:18:13.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2024-08-26T09:13:23.000Z (3 months ago)
- Last Synced: 2024-09-27T06:22:12.100Z (about 2 months ago)
- Topics: ai, audio, ballerina, openai, whisper
- Language: Ballerina
- Size: 2.01 MB
- Stars: 0
- Watchers: 49
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Codeowners: .github/CODEOWNERS
Awesome Lists containing this project
README
# Ballerina OpenAI Audio connector
[](https://github.com/ballerina-platform/module-ballerinax-openai.audio/actions/workflows/ci.yml)
[](https://github.com/ballerina-platform/module-ballerinax-openai.audio/actions/workflows/trivy-scan.yml)
[](https://github.com/ballerina-platform/module-ballerinax-openai.audio/actions/workflows/build-with-bal-test-graalvm.yml)
[](https://github.com/ballerina-platform/module-ballerinax-openai.audio/commits/master)
[](https://github.com/ballerina-platform/ballerina-library/labels/module%openai.audio)
## Overview
[OpenAI](https://openai.com/), a leading AI research organization focused on creating friendly AI for humanity, provides the [OpenAI API](https://platform.openai.com/docs/api-reference/introduction) to access its powerful AI models for tasks like natural language processing and image generation.
The `ballarinax/openai.audio` package offers APIs to connect and interact with [audio related endpoints of OpenAI REST API v1](https://platform.openai.com/docs/api-reference/audio/create) providing access to various models developed by OpenAI for audio-related tasks.
## Setup guide
To use the OpenAI Connector, you must have access to the OpenAI API through a [OpenAI Platform account](https://platform.openai.com) and a project under it. If you do not have a OpenAI Platform account, you can sign up for one [here](https://platform.openai.com/signup).
#### Create a OpenAI API Key
1. Open the [OpenAI Platform Dashboard](https://platform.openai.com).
2. Navigate to Dashboard -> API keys
3. Click on the "Create new secret key" button
4. Fill the details and click on Create secret key
5. Store the API key securely to use in your application
## Quickstart
To use the `OpenAI Audio` connector in your Ballerina application, update the `.bal` file as follows:
### Step 1: Import the module
Import the `openai.audio` module.
```ballerina
import ballerinax/openai.audio;
```
### Step 2: Instantiate a new connector
Create a `audio:ConnectionConfig` with the obtained API Key and initialize the connector.
```ballerina
configurable string token = ?;
final images:Client openAIAudio = check new ({
auth: {
token
}
});
```
### Step 3: Invoke the connector operation
Now, utilize the available connector operations.
#### Transcribe audio into input language
```ballerina
public function main(string fileName) returns error? {
byte[] fileContent = check io:fileReadBytes(fileName);
audio:CreateTranscriptionRequest request = {
model: "whisper-1",
file: {fileContent, fileName}
};
audio:CreateTranscriptionResponse response =
check OpenAIAudio->/audio/transcriptions.post(request);
}
```
### Step 4: Run the Ballerina application
```bash
bal run
```
## Examples
The `OpenAI Audio` connector provides practical examples illustrating usage in various scenarios. Explore these [examples](https://github.com/module-ballerinax-openai.audio/tree/main/examples/), covering the following use cases:
1. [International news translator](https://github.com/ballerina-platform/module-ballerinax-openai.audio/tree/main/examples/international-news-translator) - Converts a text news given in any language to english
2. [Meeting transcriber and translator](https://github.com/ballerina-platform/module-ballerinax-openai.audio/tree/main/examples/meeting-transcriber-and-translator) - Converts an audio given in a different language into text in input language and english
## Build from the source
### Setting up the prerequisites
1. Download and install Java SE Development Kit (JDK) version 17. You can download it from either of the following sources:
* [Oracle JDK](https://www.oracle.com/java/technologies/downloads/)
* [OpenJDK](https://adoptium.net/)
> **Note:** After installation, remember to set the `JAVA_HOME` environment variable to the directory where JDK was installed.
2. Download and install [Ballerina Swan Lake](https://ballerina.io/).
3. Download and install [Docker](https://www.docker.com/get-started).
> **Note**: Ensure that the Docker daemon is running before executing any tests.
4. Export Github Personal access token with read package permissions as follows,
```bash
export packageUser=
export packagePAT=
```
### Build options
Execute the commands below to build from the source.
1. To build the package:
```bash
./gradlew clean build
```
2. To run the tests:
```bash
./gradlew clean test
```
3. To build the without the tests:
```bash
./gradlew clean build -x test
```
4. To run tests against different environments:
```bash
./gradlew clean test -Pgroups=
```
5. To debug the package with a remote debugger:
```bash
./gradlew clean build -Pdebug=
```
6. To debug with the Ballerina language:
```bash
./gradlew clean build -PbalJavaDebug=
```
7. Publish the generated artifacts to the local Ballerina Central repository:
```bash
./gradlew clean build -PpublishToLocalCentral=true
```
8. Publish the generated artifacts to the Ballerina Central repository:
```bash
./gradlew clean build -PpublishToCentral=true
```
## Contribute to Ballerina
As an open-source project, Ballerina welcomes contributions from the community.
For more information, go to the [contribution guidelines](https://github.com/ballerina-platform/ballerina-lang/blob/master/CONTRIBUTING.md).
## Code of conduct
All the contributors are encouraged to read the [Ballerina Code of Conduct](https://ballerina.io/code-of-conduct).
## Useful links
* For more information go to the [`openai.audio` package](https://central.ballerina.io/ballerinax/openai.audio/latest).
* For example demonstrations of the usage, go to [Ballerina By Examples](https://ballerina.io/learn/by-example/).
* Chat live with us via our [Discord server](https://discord.gg/ballerinalang).
* Post all technical questions on Stack Overflow with the [#ballerina](https://stackoverflow.com/questions/tagged/ballerina) tag.