Amazon Transcribe is one of Amazon Web Services' (AWS) machine learning offerings. You input audio or video; Transcribe converts it to text, allowing you to identify the languages used and the number of speakers in the process. You can then take this transcription and do multiple things with it, including search, analytics, subtitles, translations, or even feeding it back into Amazon Polly to read your transcription back to you. When you start a Transcribe job, you're asked to pick out the language that's being spoken -- or have Transcribe automatically detect it for you. Also, there was really no rhyme or reason to the words and phrases I picked, other than they were the first that came to mind!

If you operate in a country with multiple official languages or across multiple regions, your audio files can contain different languages. Participants may be speaking entirely different languages or may switch between languages. Consider a customer service call to report a problem in an area with a substantial multi-lingual population. Although the conversation could begin in one language, it's feasible that the customer might change to another language to describe the problem, depending on comfort level or usage preferences with other languages. With a minimum of 3 seconds of audio, Amazon Transcribe can automatically identify and efficiently generate transcripts in the languages spoken in the audio without needing humans to specify the languages.

Subtitle creation on video content poses challenges no matter how big or small the organization. To address those challenges, Amazon Transcribe has a helpful feature that enables subtitle creation directly within the service. There is no machine learning (ML) or code writing required to get started. This post walks you through setting up a no-code workflow for creating video subtitles using Amazon Transcribe within your Amazon Web Services account. The terms subtitles and closed captions are commonly used interchangeably, and both refer to spoken text displayed on the screen.

If you are using the Amazon Transcribe service for automated speech recognition (ASR) feature in your project (especially for the English language), you had to decide whether to build a custom language model or a general model provided by AWS transcribe service. It could also be the case that you tried both options in your application. As I had some experience in trying both options in my project, here I am going to share my two cents. You used the general model to transcribe your audio or video files. You noticed that Amazon Transcribe is not able to recognize certain not-so-frequent English words or phrases that have been pronounced by speakers in audio files.

Today AWS Step Functions expands the number of supported AWS services from 17 to over 200 and AWS API Actions from 46 to over 9,000 with its new capability AWS SDK Service Integrations. When developers build distributed architectures, one of the patterns they use is the workflow-based orchestration pattern. This pattern is helpful for workflow automation inside a service to perform distributed transactions. An example of a distributed transaction is all the tasks required to handle an order and keep track of the transaction status at all times. Step Functions is a low-code visual workflow service used for workflow automation, to orchestrate services, and help you to apply this pattern.

In 2017, we launched Amazon Transcribe, an automatic speech recognition service that makes it easy for developers to add a speech-to-text capability to their applications. Since then, we added support for more languages, enabling customers globally to transcribe audio recordings in 31 languages, including 6 in real-time. A popular use case for Amazon Transcribe is transcribing customer calls. This allows companies to analyze the transcribed text using natural language processing techniques to detect sentiment or to identify the most common call causes. If you operate in a country with multiple official languages or across multiple regions, your audio files can contain different languages.