Getting started with Amazon Transcribe
Before you can create transcriptions, you have a few prerequisites:
Install the AWS CLI and SDKs (if you're using the AWS Management Console for your transcriptions, you can skip this step)
Once you complete these prerequisites, you're ready to transcribe. Select your preferred transcription method from the following list to get started.
Because streaming using HTTP/2 and WebSockets is more complicated than the other transcription methods, we advise reviewing the Setting up a streaming transcription section before getting started with these methods.
Signing up for an AWS account
You can sign up for either a free tier
When setting up your account, make note of your AWS account ID because you need it to create an IAM user or group.
Installing the AWS CLI and SDKs
To use the Amazon Transcribe API, you must first install the AWS CLI. The current AWS CLI is version 2. You can find installation instructions for Linux, Mac, Windows, and Docker in the AWS Command Line Interface User Guide.
Once you have the AWS CLI installed, you need to configure it for your security credentials and AWS Region.
If you want to use Amazon Transcribe with an SDK, click on your preferred language for installation instructions:
-
AWS SDK for Python (Boto3)
— batch transcriptions only -
Python
— streaming transcriptions only
Creating an IAM user
IAM, or Identity and Access Management, is a means of controlling which users can access which resources. All AWS services use IAM credentials and it is best practice to use an IAM admin user to access your resources. Using your AWS account root user credentials to access resources is not recommended. To learn more about IAM, see What is IAM?
You can create an IAM admin user with the AWS Management Console or AWS CLI. For instructions, see Creating your first IAM admin user and user group. For information on signing in to your account using IAM user credentials, refer to How IAM users sign in to your AWS account.
For AWS CLI-specific IAM instructions, see Using an IAM role in the AWS CLI.
Creating an Amazon S3 bucket
Amazon S3 is a secure object storage service. Amazon S3 stores your files (called objects) in containers (called buckets).
To run a batch transcription, you must first upload your media files into an Amazon S3 bucket. If you don't specify an Amazon S3 bucket for your transcription output, Amazon Transcribe puts your transcript in a temporary AWS-managed Amazon S3 bucket. Transcription output in AWS-managed buckets is automatically deleted after 90 days.
Learn how to Create your first S3 bucket and Upload an object to your bucket.