Home > Categories > Recognition and synthesis of things > Speech Recognition (ASR) > Amazon Transcribe

Amazon Transcribe

Rating:

4.7 / 5.0

Tags

Speech Recognition, ASR, NLP, Cloud Service, AWS, Transcription, Audio Analysis

Categories:
Data AnalysisEthical AI and SafetyHealthcareNatural language processingRecognition and synthesis of things
Creator Amazon Web Services (AWS)
Date 2017-11-29
Platforms Cloud API, AWS Console
Status Active
Website aws.amazon.com
Price Model Pay-as-you-go
Sections:
AI Risk ManagementBig Data ProcessingChatbots and Conversational AIInformation ExtractionPatient Data ManagementSpeech Recognition (ASR)

Pricing Details

Pay-as-you-go based on the number of minutes of audio processed. A free tier is available for a limited number of minutes per month.

Features

Automatic speech recognition (ASR), batch transcription, streaming transcription, speaker diarization, entity identification, profanity filtering, multilingual support, API access.

Integrations

API and SDKs for integration into applications, web services, and workflows. Integration with other AWS services (e.g., S3, Lambda).

Preview

Amazon Transcribe is an automatic speech recognition (ASR) service from Amazon Web Services (AWS) that allows developers to easily add speech-to-text capabilities to their applications. It can transcribe audio and video files, as well as streaming speech. Transcribe supports numerous languages and dialects, is capable of recognizing multiple speakers (diarization), identifying entities, and filtering profanity. The service is useful for generating subtitles, analyzing calls, transcribing media content, and other tasks requiring the conversion of spoken language into text. It is available via API and the AWS console.