Digital Nirvana products in the spotlight include Trance, MonitorIQ and Metadator.
Digital Nirvana’s spring demonstration of products will focus on its latest tech designed to help streamline broadcast monitoring and content generation.
The first such product is Trance, a cloud-based transcription, closed captioning and translation workflow. The cloud-based architecture supports an integrated automatic speech-to-text engine and easy-to-use interface. The system allows for captions to be generated per presets that can conform with specific style guides. Trance can automatically generate transcripts, including in multiple languages. It can also centralize workflows like job allocation, caption edits, role assignment, report generation and status monitoring. The ability to ingest Avid assets directly for caption generation and/or metadata enhancement is available as well. Users can access media assets from cloud storage, Avid Media Central, SFTP, local servers or via an API.
The next generation MonitorIQ 7.0 compliance and broadcast monitoring system will also be on hand. This latest version features one-touch access to content and associated metadata for content review, analysis, troubleshooting and proof of performance. It has advanced analysis for comparing SCTE messages. There are also new Clip and Share tools for content sharing and collaboration. In addition, MonitorIQ 7.0 can be integrated with Digital Nirvana’s Media Service IQ, which adds AI-based cloud microservices that include transcript generation for ads and content, caption quality assessment, caption realignment and video intelligence for objects, ads, logos and facial recognition.
Metadator rounds out Digital Nirvana’s offerings. This software-as-a-service platform automates metadata generation for production, preproduction and live content, and now can integrate with Avid Interplay for the creation of automatic transcripts, labels for objects, faces, logos and other metadata with locators for Avid users. Additional features include on-screen text recognition, shot-change detection and explicit content detection.