Automatic content redaction supported by Amazon Transcribe

Amazon Transcribe uses advanced machine learning technologies to identify speech in audio files and transcribe them into text and this process called automatic speech recognition (ASR). For example, you can transcribe the audio track from a video recording to create closed captioning for the video. Similarly, it can be used to transcribe customer service calls, for subtitling, and to create metadata for media resources to produce a completely searchable archive. Now, you can command Amazon Transcribe’s content redaction feature to automatically pull out sensitive personally identifiable information (PII) from your transcription results. State-of-the-art machine learning technology utilised by Amazon Transcribe to correctly recognise and take out PII. PII removed adds social security number, credit card/bank account details and contact details like name, email address, phone number and mailing address. PII redaction allows contact centers to analysis and share transcripts to better the customer service experience, train agents, and find new business chances during retaining their qualities for managing PII. Amazon Transcribe’s redaction feature is purpose-built for recognising PII in conversational transcripts and is most precise for both numeric and non-numeric PII. Now this Automatic content redaction feature is accessible for US English with asynchronous transcription jobs in the following AWS regions: US East (N. Virginia), US West (N. California), US East (Ohio), US West (Oregon), Asia Pacific (Mumbai), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Hong Kong), Asia Pacific (Tokyo), Canada (Central), EU (Frankfurt), EU (Ireland), EU (London), EU (Paris), South America (Sao Paulo), Middle East (Bahrain), and AWS GovCloud (US-West). To know the pricing details, refer Automatic content redaction pricing. And to get further information, read documentation

Now Amazon Transcribe’s Speech-to-text feature is available in 8 further languages

Amazon Transcribe is an automatic speech recognition (ASR) service that based on advanced machine learning technologies which can use to convert audio files into text format and to build applications that incorporate the content of audio files. Amazon Transcribe can be utilized for plenty applications. For example, you can transcribe the audio track from a video recording to generate subtitles for the video. Amazon Transcribe can transcribe audio files saved in common formats, like WAV and MP3, with time stamps for each word so that you can simply find the audio in the original source by looking for the text. Amazon Transcribe is constantly learning and enhancing to boost the progress of language. You can examine audio files stored in Amazon S3 with the help of Amazon Transcribe API. Besides, you can send a live audio stream to Amazon Transcribe and get a stream of transcripts in real time. Now Amazon Transcribe is available in further 8 languages - Irish English, Scottish English, Welsh English, Dutch, Farsi, Indonesian, Portuguese, and Tamil languages. With these new supported languages, Amazon Transcribe is now totally available in Modern Standard Arabic, Chinese Mandarin-Mainland, Dutch, Australian English, British English, Indian English, Irish English, Scottish English, US English, Welsh English, French, Canadian French, Farsi, German, Indian Hindi, Indonesian, Italian, Korean, Portuguese, Brazilian Portuguese, Russian, Spanish, US Spanish, and Tamil languages. To get the further information, refer Amazon Transcribe or Documentation.

Now WebSocket Assisted By Amazon Transcribe Streaming

Amazon Transcribe applies advanced machine learning technologies to identify speech in audio files and translate them into text. Amazon Transcribe can utilize to change audio to text and to build applications which include the audio file content. Example, you can transcribe the audio track from a video recording to create closed captioning for the video. Amazon Transcribe offers assistance to WebSocket protocol for streaming transcription. Users can open a bidirectional connection to send an audio stream to the service, and in return, receive a stream of text in real time. Before this introduction, streaming transcription was available via HTTP/2 streams. WebSocket protocol assistance produces integrations simple for customers with WebSocket-based clients. You can utilize streaming transcription to efficiently and precisely record transcripts for multiple use cases, like transcribing calls for contact centers, automatically produce subtitles for media, also recording meeting notes for business efficiency. To get more information about this WebSocket feature, refer documentation. This new feature is accessible in each region where streaming service is accessible, to know refer AWS Region documentation.