Amazon Transcribe Toxicity Detection
Amazon Transcribe Toxicity Detection, an ML-powered, voice-based toxicity detection capability, which leverages both audio and text-based cues to identify and classify toxic language including hate speech, harassment and threats. In addition to text, Amazon Transcribe Toxicity Detection uses speech cues, such as tone and pitch to hone in on toxic intent in speech. Toxic content is flagged and classified across seven categories including sexual harassment, hate speech, threat, abuse, profanity, insult, and graphic. This allows moderators to take focused action rather than reviewing entire conversations.
Improve user and brand safety
Review a select few or hours of audio conversations for offensive and innappropriate speech. Proactively provide a safe online environment for both users and brands.
Automatically analyze audio conversations at scale to highlight areas with toxic content. Reduces the content, human moderators have to review by up to 95%.
Easy to use
Configure Amazon Transcribe Moderation by enabling a few options in the AWS console, no machine learning experience is required.
Amazon Transcribe Toxicity Detection classifies toxic audio content and provides a confidence score (0 to 1) for the following seven categories: sexual harassment, hate speech, violence/threat, abuse, profanity, insult, and graphic.
Easily filter results by managing threshold values for each toxic content category.
Broad media file support
Transcribe Toxicity Detection can analyze the following media formats: MP3, MP4, WAV, FLAC, AMR, OGG, or WebM formats.
Post call analytics for your contact center with Amazon language AI services
Andrew Kane, Connor Kirkpatrick, Franco Rezabek, Steve Engledow, and Bob Strahan
Live call analytics for your contact center with Amazon language AI services
Bob Strahan, Sagar Khasnis, Oliver Atoa, and Court Schuett
Visit the pricing page.
Instantly get access to the AWS Free Tier.
Get started building with Amazon Transcribe Toxicity Detection in the AWS Management Console.