This PR introduces the MonsterAPI integration into the Whisper Playground, aiming to enhance the audio transcription capabilities of our application. By leveraging MonsterAPI's robust transcription features, we provide users with more accurate and flexible transcription options. This integration includes the ability to specify various transcription parameters such as language, transcription format, and the option to diarize or remove silence from the audio.
Key Features Added:
MonsterAPI client setup for audio file transcription.
Configurable transcription settings through the UI, including language selection, beam size, and silence removal.
Environment variable support for secure API token management.
Technical Changes:
Added MonsterApiClient.js to handle API requests to MonsterAPI.
Updated App.js to include MonsterAPI transcription logic in the audio processing flow.
Introduced new environment variable REACT_APP_MONSTERAPITOKEN for API authentication.
Enhanced the settings section in the UI to include additional transcription options provided by MonsterAPI.
Dependencies Added:
monsterapi: A hypothetical package to interact with MonsterAPI (Note: replace with the actual package if available).
Setup Instructions:
To utilize MonsterAPI's transcription service, an API token is required. Follow these steps to configure your environment:
Obtain an API token from MonsterAPI.
Create a .env file in the root directory of the project (if not already present).
Ensure the .env file is included in your .gitignore to prevent exposing your API token.
Testing:
Conducted manual tests to ensure audio transcription is working as expected with various audio samples.
Verified that the new UI elements for configuring transcription options are functional and user-friendly.
Ensured backward compatibility with existing transcription methods in the Whisper Playground.
Screenshots:
Notes for Reviewers:
Please review the changes focusing on the integration of MonsterAPI and the added environment variable management. Feedback on the UI enhancements for setting transcription options would also be appreciated.
Title:
Description:
This PR introduces the MonsterAPI integration into the Whisper Playground, aiming to enhance the audio transcription capabilities of our application. By leveraging MonsterAPI's robust transcription features, we provide users with more accurate and flexible transcription options. This integration includes the ability to specify various transcription parameters such as language, transcription format, and the option to diarize or remove silence from the audio.
Key Features Added:
Technical Changes:
MonsterApiClient.jsto handle API requests to MonsterAPI.App.jsto include MonsterAPI transcription logic in the audio processing flow.REACT_APP_MONSTERAPITOKENfor API authentication.Dependencies Added:
monsterapi: A hypothetical package to interact with MonsterAPI (Note: replace with the actual package if available).Setup Instructions:
To utilize MonsterAPI's transcription service, an API token is required. Follow these steps to configure your environment:
.envfile in the root directory of the project (if not already present)..envfile:.envfile is included in your.gitignoreto prevent exposing your API token.Testing:
Screenshots:
Notes for Reviewers:
Please review the changes focusing on the integration of MonsterAPI and the added environment variable management. Feedback on the UI enhancements for setting transcription options would also be appreciated.