Skip to main content

Amazon Transcribe Documentation

Audio inputs

Transcribe is designed to process live and recorded audio or video input to provide transcriptions for search and analysis.

Streaming & batch transcription

You are enabled to process your existing audio recordings or stream the audio for transcription. Using a secure connection, you are enabled to send a live audio stream to the service, and receive a stream of text in response.

Domain specific models

Models are designed to be tuned to telephone calls or multimedia video content.

Language identification

Amazon Transcribe is designed to identify the dominant language in an audio file and generate transcriptions.

Transcripts

Punctuation & number normalization

Amazon Transcribe is designed to add punctuation and number formatting to produce transcriptions.

Timestamp generation

Amazon Transcribe is designed to return a timestamp for each word.

Recognize multiple speakers

Amazon Transcribe is designed to recognize and attribute speaker changes in the text.

Channel identification

Amazon Transcribe is enabled to produce a single transcript from contact center audio files, annotated by channel labels.

Customize your output

Custom vocabulary

With custom vocabulary, you are enabled to add new words to the base vocabulary to generate more accurate transcriptions for domain-specific words and phrases.

Custom language models

When needed, you are enabled to build and train your own custom language model (CLM) for your use case and domain.

Privacy and Security

Transcribe is designed to help you mask or remove words that are sensitive or unsuitable for your audience from transcription results.

Vocabulary filtering

You are enabled to specify a list of words to remove from transcripts with vocabulary filtering.

Content redaction

When instructed, Amazon Transcribe is designed to help customers identify and redact sensitive personally identifiable information (PII) from the supported language transcripts. .

Toxic audio content detection

Amazon Transcribe Toxicity Detection is designed to flag problematic language into categories for human moderators to review.

Amazon Transcribe Call Analytics

Amazon Transcribe is designed to extract conversation insights like call sentiment and speech loudness.

Call summarization

Amazon Transcribe is designed to generate call summaries.

Call analytics & conversation insights

Using machine learning, you are enabled to apply speech-to-text and natural language processing capabilities for conversation insights. You are then able to integrate those insights into your inbound and outbound call analytics applications.

Compliance & monitoring with call categorization

You are enabled to monitor your calls to help track compliance with company policies or regulatory requirements. You are enabled to build and train your own categories based on your specified criteria.

Produce call transcripts

You are enabled to give your agents access to the conversation details from past interactions. The turn-by-turn transcripts are designed to provide insights.

Amazon Transcribe Medical

You are enabled to transcribe your medical conversations with Transcribe Medical, a speech recognition (ASR) service.

Dictation mode

Designed to transcribe single-speaker audio found in medical dictation use cases.

Conversational mode

Designed to transcribe multi-speaker conversational audio.

Medical specialties

Designed to transcribe speech to text across a range of medical specialties.

Batch API

Designed to transcribe recorded medical audio files at scale.

Custom vocabulary

Designed to boost transcription accuracy by using custom vocabulary for potentially out-of-lexicon terminology.

Channel identification

Designed to concurrently transcribe multi-channel audio and get one transcript.

Speaker diarization

Designed to separate speech from different speakers within mono-channel audio.

Additional Information

For additional information about service controls, security features and functionalities, including, as applicable, information about storing, retrieving, modifying, restricting, and deleting data, please see https://docs.aws.amazon.com/index.html. This additional information does not form part of the Documentation for purposes of the AWS Customer Agreement available at http://aws.amazon.com/agreement, or other agreement between you and AWS governing your use of AWS’s services.