Digital Nirvana Launches New Automation for Avid Interplay

RADIO ONLINE | Tuesday, July 20, 2021 | 8:49am CT

Digital Nirvana has announced MetadataIQ, a new metadata automation tool for content producers using the Avid media platform. A secure and scalable software-as-a-service (SaaS) solution, MetadataIQ offers off-the-shelf integration with Avid Interplay to automate the end-to-end process of generating speech-to-text and video intelligence metadata for Avid-based assets while automatically submitting media for transcription, captioning, and translations from within the existing workflow.

MetadataIQ allows operators to create and ingest different types of metadata - including speech-to-text, facial recognition, OCR, logos, and objects, each with customizable marker durations and color codes for easy identification - that can be accessed via the Avid MediaCentral™ environment. Editors simply type a search term within Interplay or MediaCentral, identify the relevant clip, and start creating content. For VOD and content repurposing, video intelligence metadata aids in product placement/replacement and accurately identifying ad spots.

The platform is the first to offer on-premises transcoding and intelligent extraction of audio files to generate speech-to-text transcripts. Users aren't required to create a low-res proxy or manually import files into Avid MediaCentral. MetadataIQ automatically generates speech-to-text transcripts for file-based assets in addition to streaming speech-to-text transcripts from growing audio assets in real time. Operators have the option of sending transcripts to Digital Nirvana's processing centers for high-quality, human-curated output, which is returned within Interplay.

"By delivering complete automation over the generation and ingestion of relevant metadata as locators into Avid, MetadataIQ helps editors accurately identify relevant content to save time and effort," said Hiren Hindocha, CEO, Digital Nirvana. "For example, we've had users report that the process of creating new content has been reduced from 15 hours to two hours. In addition, our platform replaces several traditional manual processes - from creating low-res proxies to submitting files to third parties for transcripts, captions, and translations - to increase the efficiency of production, preproduction, and live content creation processes."