Getting Started with AudioShake's API

The AudioShake API is a powerful tool that developers can use to quickly and efficiently use AudioShake's models to transcribe or seperate their audio files, integrated into their own applications. You can integrate our API to provide better audio experiences, contact AudioShake for custom latency examples at support@audioshake.ai.

You can see examples of our API implementations on our case studies page.

Overview

1. To use the AudioShake API, please contact us for a token at support@audioshake.ai.

2. After recieving an API key, check Authentication for information about how to use it to access the API.

3. The first step in posting a job via our API is to upload the file you wish to process. File Upload explains how to use the API to upload a file.

4. After you have uploaded a file, you can now use post a job using one of our models.

   • Instrument Stem Seperation outlines how to post a job that separates instruments from music
   • Dialogue, Music, & Effects Seperation outlines the process to post a job that separates clean dialogue, filters out music, or filters out background noise and effects.

5. The API can also transcribe audio & align that transcription, providing precise timestamps to the transcription. Information about how to use the API to post transcription & alignment jobs can be found on the associated page

Detailed descriptions of jobs & parameters can be found on our Data Models page.