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.
Tip
If you're new to Amazon Transcribe or would like to explore our features, we recommend using
the AWS Management Console
Because streaming using HTTP/2 and WebSockets is more complicated than the other transcription methods, we recommend reviewing the Setting up a streaming transcription section before getting started with these methods. Note that we strongly recommend using an SDK for streaming transcriptions.
Sign up for an AWS account
To get started with AWS, you need an AWS account. For information about creating an AWS account, see Getting started with an AWS account in the AWS Account Management Reference Guide.
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 must configure it for your security credentials and AWS Region.
If you want to use Amazon Transcribe with an SDK, select your preferred language for installation instructions:
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.
Creating an IAM policy
To manage access in AWS, you must create policies and attach them to IAM identities (users, groups, or roles) or AWS resources. A policy defines the permissions of the entity it is attached to. For example, a role can only access a media file located in your Amazon S3 bucket if you've attached a policy to that role which grants it access. If you want to further restrict that role, you can instead limit its access to a specific file within an Amazon S3 bucket.
To learn more about using AWS policies see:
For example policies you can use with Amazon Transcribe, see
Amazon Transcribe identity-based policy examples. If you want to generate custom
policies, consider using the
AWS
Policy Generator
You can add a policy using the AWS Management Console, AWS CLI, or AWS SDK. For instructions, see Adding and removing IAM identity permissions.
Policies have the format:
Amazon Resource Names (ARNs) uniquely identify all AWS resources, such as an
Amazon S3 bucket. You can use ARNs in your policy to grant permissions for specific actions to
use specific resources. For example, if you want to grant read access to an Amazon S3 bucket
and its sub-folders, you can add the following code to your trust policy's Statement
section:
{ "Effect": "Allow", "Action": [ "s3:GetObject", "s3:ListBucket" ], "Resource": [ "arn:aws:s3:::amzn-s3-demo-bucket", "arn:aws:s3:::amzn-s3-demo-bucket/*" ] }
Here's an example policy that grants Amazon Transcribe read (GetObject,
ListBucket) and write (PutObject) permissions to an
Amazon S3 bucket, amzn-s3-demo-bucket, and its sub-folders: