In the last 18 months, Box said it has seen over 50 percent growth in audio files alone. With the rapid growth of audio-first social networking, the explosion of podcasts, more people streaming music and entertainment than ever, coupled with higher demand for video content on social media, the need for easily accessible and premium quality audio has become important for content producers of all sizes.

The new solution leverages Dolby’s Dolby.io cloud-based software suite of automated tools that can be applied to audio files that have been finished and need slight tweaking, or for content that’s been recorded, cut down, and needs to be cleaned up before being shared. It supports the input and output of common digital audio formats like .WAV and MP3. Users can also use other companies’ audio processing tools as a part of their preferred workflow.

Dolby said the new solution is designed to help media organizations that often lack the time (or resources) to send valuable content to a recording studio where it would be mastered professionally by an experienced audio engineer. Real-world examples cited include a film studio processing thousands of hours of video footage for an upcoming documentary, a leading tech blog that has to quickly upload 20 new podcasts episodes during a trade show, or a professional football team that needs to quickly put out a sideline interview on social media for their fans.

Box Enterprise customers can now install Dolby.io into their Box account to give their users access to Dolby audio processing with a simple right-click of the mouse.

A Box customer has a choice of a fully automated mode where the Dolby.io APIs will analyze the content and immediately apply the right combination of processing to improve audio quality. In addition, there’s no limit to file size, with the companies claiming to have tested content up to 24 hours long with no hiccups.

“The great thing about audio enhancement in the cloud is that all you have to do is upload your content, and Dolby and Box take over, regardless of your connection speed,” said Sripal Mehta, Senior Director of Media Services at Dolby Labs.

“What’s unique to our algorithms is that we perform scene analysis to understand when there’s speech, music, and other sounds to apply the right type of processing to each scene,” he said. “The API has a comprehensive set of audio processing capabilities powered by a combination of deep-learning and signal processing-based algorithms—including background noise reduction; dynamics processing, speech-based loudness correction; sibilance, plosive, and mouth-click reduction; and dynamic equalization.”

Dolby is now in discussion with several live sports organizations to help them ensure that all of the content surrounding a game or match sounds great.

"Dolby.io can help improve the quality of the short-form content that’s produced before, during, and after the game - locker room interviews, courtside interviews, player bios, and more,” Mehta, said. “A lot of these short clips don’t get to the audio production team, so now the content teams dealing with this type of content have tools to process those clips for immediate broadcasting while the production teams can focus on the highest value content.

“A lot of high-value broadcast is shared on-demand – via social media, via a league’s website, or through their apps,” he said. “The Dolby.io integration, and the technology underpinning it, can help increase quality and reduce turn-around time for short-form content, or even for full events that don’t ever get in front of an audio team. Delivering great audio is hard. We want to help make it easier.”

By offering simple yet intelligent APIs that improve media quality, Dolby is delivering world-class sound through specialized, highly automated code… no audio engineer required.