AWS Amazon Transcribe - Speech to Text Converter - 1


To run the Live Transcribe Demo correctly, remove Envato iFrame on the top right corner, for some reason envato’s frame blocking secure connection with our server.


AWS Amazon Transcribe uses a deep learning process called automatic speech recognition (ASR) to convert speech to text quickly and accurately. Using Automatic Speech Recognition (ASR) technology, customers can choose to use Amazon Transcribe for a variety of business applications, including transcription of voice-based customer service calls, generation of subtitles on audio/video content.

To use Amazon Transcribe you store your audio file in an Amazon S3 bucket. The output from the transcription job is also stored in an S3 bucket.

You can also use Amazon Transcribe to transcribe streaming audio in real-time. You send Amazon Transcribe a stream of audio and Amazon Transcribe returns a stream of JSON objects containing the transcription of the audio. Convert your speech to text easily with the Amazon Transcribe Speech to Text Converter.

Set Up:

  • NOTE: Good knowledge (or at least willingness to learn) of AWS Management Console, Amazon Lambda and Amazon SES services are required
  • If response by email is not needed, then there is no need to use Amazon Lambda and Amazon SES services. You must include your AWS IAM User Access and Secret Access Key and your AWS Bucket Name and you are all set!

Benefits of Amazon Transcribe:

  1. Deep Learning ASR Technology from Amazon Web Services
  2. Support for over 30 Languages and Accents
  3. Support for various audio extension: MP3 | MP4 | WAV | FLAC
  4. Up to 4 Hours of audio file length
  5. Up to 2GB audio file size
  6. Support for custom vocabulary
  7. Up to 60min/month during FREE Tier
  8. Transcribe streaming audio with HTTP/2 and Websockets
  9. Lowest cost, only $0.0004/seconds
  10. Pay as you go payment model
  11. Minimum charge of 15 seconds per request
  12. Record and Upload audio files
  13. Easy to customize

AWS Amazon Transcribe - Speech to Text Converter - 2

Cost of Running Amazon Transcribe – Speech to Text Converter:

  • You can use any hosting platform as you prefer for the application itself
  • AWS Account (Free to Open – You will be on Free Tier for the 1st year)
  • Amazon S3 Storage Cost (For Data Storage and Data Traffic Out)

With Amazon Transcribe, you pay-as-you-go based on the seconds of audio transcribed per month. It’s easy to get started with the Amazon Transcribe Free Tier. Upon signup, start analyzing up to 60 minutes of audio monthly, free for the first 12 months.

Amazon Transcribe API (including streaming transcription) is billed monthly at a rate of $0.0004 per second. Usage is billed in one-second increments, with a minimum per request charge of 15 seconds.

AWS Amazon Transcribe - Speech to Text Converter - 3

Installation Instructions:

Setup Requirements:
  • AWS PHP SDK v3 is Required – Setup Link
  • AWS IAM User with Transcribe/Lambda/SES Access Policies attached – Setup Link
  • Amazon S3 Bucket with Public Access – Setup Link
  • Also Listed and Explained in the Documentation
AWS Backend Architecture of the Application:

AWS Amazon Transcribe - Speech to Text Converter - 4


Release Notes – Change Logs:

24.02.2020 - 1.0.0
     - Initial Release

AWS Amazon Transcribe - Speech to Text Converter - 5AWS Amazon Transcribe - Speech to Text Converter - 6