Skip to main content
TUTORIAL

Create an Audio Transcript with Amazon Transcribe

Introduction

Overview

In this step-by-step tutorial, you will learn how to use Amazon Transcribe to create a text transcript of a recorded audio file using the AWS Management Console. Amazon Transcribe is an automatic speech recognition (ASR) service that makes it easy for developers to add speech-to-text capability to their applications. Using the Amazon Transcribe API, you can analyze audio files stored in Amazon Simple Storage Service (Amazon S3) and have the service return a text file of the transcribed speech.

As a developer, creating transcriptions of customer service calls or generating subtitles on audio and video content are common challenges requiring speech-to-text capabilities. This challenge could be solved by building your own machine learning models from scratch. However, this option is time-intensive, expensive, and requires machine learning expertise. Instead of taking the difficult route, you can use Amazon Transcribe, a pre-trained and fully managed service, which provides fast and high-quality transcriptions.

In this tutorial you will download a sample audio file then upload it to an Amazon S3 bucket that you will create. Then you will use Amazon Transcribe to create a transcript from the sample audio clip using the AWS Management Console.

This tutorial is a demo of the functionality that is available when using the AWS CLI or the Amazon Transcribe API. For production or proof of concept implementations, we recommend using these programmatic interfaces rather than the Amazon Transcribe Console.

Implementation

Beginner

10 minutes

Free Tier eligible

  • AWS account

  • Recommended browser: The latest version of Chome or Firefox

Note: Accounts created within the last 24 hours might not yet have access to the services required for this tutorial.

July 5, 2022

Create an S3 bucket and upload sample

In this step, you will download a sample audio file, create an S3 bucket, then upload the sample file to the S3 bucket. Amazon Transcribe accesses audio and video files for transcription exclusively from S3 buckets.

1. Download the file

To download the sample audio file to transcribe later in the tutorial, choose transcribe-sample.mp3.

2. Open the console

Select AWS Management Console to open the console in a new browser window, so you can keep this step-by-step guide open. When the screen loads, enter your user name and password to get started.

Using the Region drop down, select a Region that has Amazon Transcribe.

Missing alt text value

3. Open the S3 console

Type S3 in the search bar and select S3 to open the console.

Missing alt text value

4. Create a bucket

In the S3 dashboard choose Create bucket.

If this is the first time you have created a bucket, you will see a screen that looks like the image pictured here.

If you have already created S3 buckets, your S3 dashboard will list all the buckets you have created.

Missing alt text value

5. Enter a bucket name

Enter a unique bucket name. Bucket names must be unique across all existing bucket names in Amazon S3. There are a number of other restrictions on S3 bucket names as well.

Then select a Region to create your bucket in.

Missing alt text value

6. Review configuration details and create bucket

You have the ability to set up permissions for your S3 bucket. Leave the default values and scroll down.

You have many useful options for your S3 bucket including Versioning, Server Access Logging, Tags, Object-level Logging, and Default Encryption. We won't enable these features for this tutorial.

Select Create bucket.

Missing alt text value

7. Select your bucket

You will see your new bucket in the S3 console. Click on your bucket’s name to navigate to the bucket. Your bucket name will not be the same as pictured in the screenshot to the right.

Missing alt text value

8. Upload the sample file

You are in your bucket’s home page.

Select Upload.

Amazon S3 bucket interface showing an empty bucket named "mysuperawsbucket" with an orange "Upload" button highlighted.

9. Select the sample file and upload it

Upload the transcribe-sample.mp3 file by selecting Add files and selecting the file or dragging the transcribe-sample.mp3 file to the upload box.

Select Upload.

AWS S3 upload interface showing a file named "transcribe-sample.mp3" ready to be uploaded to the "mysuperawsbucket" bucket, with options to add files or folders and an orange "Upload" button.

10. Copy the S3 URI

On successful upload, select the transcribe-sample.mp3 file in your bucket. A file detail page will be displayed for the transcribe-sample.mp3 file.

Copy the S3 URI link to the file and save it for use later in the tutorial.

Screenshot of an Amazon S3 bucket interface showing details of an MP3 file, including its S3 URI, size, last modified date, and region, with a "Copy S3 URI" button highlighted.

Create transcription job

In this step, you will create and run a transcription job using the Amazon Transcribe console.

1. Open the Transcribe console

From the top menu bar, select Services then begin typing Transcribe in the search bar and select Amazon Transcribe to open the service console.

Missing alt text value

2. Open the Transcription jobs page

On the Amazon Transcribe console main page, open the navigation pane and click Transcription jobs.

Screenshot of the Amazon Transcribe webpage showcasing automatic speech recognition features, navigation menu, and options to create transcripts, call analytics jobs, or medical transcripts.

3. Create Transcription job

On the Transcription jobs page, click Create job.

Screenshot of the Amazon Transcribe dashboard showing the "Transcription jobs" section with no resources displayed and a "Create job" button highlighted.