The Rev.ai API, Powered by Rev’s Speech Engine, Accurately Converts Live Audio to Text as It Happens

Rev.ai, an automatic speech recognition service from Rev.com, launched real-time audio transcription. Powered by Rev’s proprietary speech engine, the Rev.ai API makes it easy for developers to build speech recognition directly into applications and services. The new capability processes live audio or video and returns transcripts or captions in real time.

The instant results from real-time speech recognition offer wide-ranging benefits, from increasing accessibility to unlocking insights and triggering immediate action, such as deploying an ambulance or bringing a supervisor on a call. For example:

• Large customer support teams can utilize AI to monitor and look for keywords, such as “supervisor,” and trigger the appropriate action, enabling sophisticated analytics to automate insights.
• Media companies can add live captions to their videos.
• Conferences and events are able to stream videos with real-time captions of presentations and sessions as they’re being given so that everyone is able to fully participate.

Marketing Technology News: Accenture and SAP Build Prototype that Uses Distributed Ledger Technology to Enable More Efficient, Secure and Reliable Payments Between Banks and Customers

“Having accurate transcripts and captions is a major factor in our business, and Rev.ai is by far the most reliable provider in this space,” said streamGo’s Production Director, Richard Lee. “Accuracy has long been a crucial need, but the technology hasn’t been up to par. Rev.ai is the first and only provider that allows us to meet customer expectations. With automated live captions, we’ll be able to fulfill accessibility requirements for webcasts without the premium cost of live human captioners.”

A one-stop shop for enterprise speech services, Rev.ai offers the highest accuracy of any AI speech recognition engine. Rev.ai helps businesses quickly and efficiently do more with their audio and video content, including:

• Increasing accessibility: Easy-to-read transcripts include punctuation and capitalization for quickly searchable notes.
• Customer service and call center agent quality monitoring: Use speech to text and artificial intelligence to monitor and score 100 percent of calls at a lower cost and faster throughput rate.
• Cataloging archives for broadcast and media: All transcripts are searchable by specific words and phrases. They are also easy to edit.

Marketing Technology News: Demand Spring Congratulates Grand & Toy’s Nadia Milani On Being Named to the 2019 Fearless 50 List

Using accuracy benchmarking metrics, Rev.ai beat all other speech-to-text solutions on the market, with a 13.9% error rate—better than Google Speech-to-Text (15%), Amazon Transcribe (18%) and Microsoft Azure Speech-to-Text (18%). Rev.ai is able to tackle more complicated vocabulary, powered by a deep learning model trained on Rev’s unique data set that includes millions of hours of human-transcribed audio content.

“Since launching Rev.ai, we’ve prioritized delivering fast and accurate speech recognition for our customers through our unique API,” Rev.ai General Manager Jay Lee said. “We developed real-time audio transcription to meet market demand beyond the asynchronous market, and provide customers—from podcasters to call centers—with deeper speech-to-text capabilities.”

The easy-to-use Rev.ai API comes with software development kits (SDKs), comprehensive documentation and expert support. Prices start at $0.035 per audio minute with no hidden fees.

Marketing Technology News: Lotame Launches “Cartographer” New ID Solution to Power People-Based Marketing Campaigns