ENCO will emphasize its latest live production and dynamic presentation innovations for AV environments at InfoComm next month, highlighting the “ower of AI for reliable, real-time conversions of text and speech.”
In addition to debuting its latest live captioning and translation system for AV audiences, ENCO will unveil a new text-to-speech solution that uses synthetic voice for instant audio creation. ENCO will also demonstrate its award-winning virtual production system, accentuating the value of AR/VR/XR graphics for live event production.
“AI has evolved into a mature technology that allows us to improve the accuracy of speech and text conversions,” said Ken Frommert, president, ENCO. “That includes live captioning, multi-lingual translations and text-to-speech audio to help users engage wider audiences and ensure ADA compliance. We therefore see strong opportunity for our AI and automation innovations in live production and staging environments for corporate events, worship services and entertainment performances, as well as our powerful all-in-one virtual production solution with augmented reality capabilities.”
Meet enCaption Sierra
Introduced at NAB last month, enCaption Sierra represents the latest in fast, accurate automated conversion and delivery of captions in AV and broadcast environments. enCaption Sierra applies AI and large language models to live captioning, with new benchmarks attained in speed and accuracy same as each prior enCaption system. enCaption Sierra brings ENCO’s market-leading automated captioning technology together with a captioning encoder to create an all-in-one solution for on-prem environments and containerized deployment options for cloud. enCaption Sierra can be delivered on Windows or Linux operating systems and is managed and monitored from a web browser.
enCaption Sierra’s modern GUI features a “simple calendar scheduler and various configuration settings, including custom dictionaries, word models, filtering and bilingual language options.” The same improvements are present in Sierra’s integrated enTranslate module, which uses machine translation and grammatical structure analysis to deliver captions for up to 37 languages simultaneously. ENCO also adds new languages to enTranslate’s engine on a consistent basis, with three new languages recently added as well as support for a bilingual language model for Spanish-English content.
Compliant Text-to-Speech
InfoComm marks the global debut of ENCO’s AiM audio insertion manager, a new text-to-speech solution that provides a better experience for visually impaired audiences. AiM’s AI-driven voice modeling and low-latency text-to-speech engine automatically generates natural-sounding synthetic voices for immediate or pre-scheduled delivery, allowing businesses, airports, transit centers, venues and other users to make dynamic announcements as required. AiM also provides users with multiple voice options that strike the appropriate tone for the audience, and the ability to provide real-time audio translations via ENCO’s proven enTranslate technology.
“AI development allows us to effectively generate naturally human-sounding voices that are more clearly audible and easier to follow than earlier computer-generated voices,” said Frommert, who adds that AiM is compliant with ADA and 21st Century CVAA guidelines. Similar to enCaption Sierra, AiM also builds in a customized dictionary that can easily manage local dialects and unique spellings.
Qimera Virtual Production for AV/VR/XR
ENCO will also show its Qimera Virtual Production system, an Unreal Engine-based virtual compositing tool that allows content creators to create advanced virtual sets and augmented reality graphics anywhere. ENCO will highlight how the complete solution delivers advanced virtual production technology and AR/VR/XR graphics at a very affordable price point for all budgets, opening new doors for corporations, universities, sports productions and live event venues once priced out of the market.
The Qimera ecosystem is easy to deploy, manage and operate, and doesn’t require businesses to increase their payroll upon entering the virtual, augmented and mixed reality universe. Its compositing tools were built with modern production workflows in mind, beginning with its easy and intuitive user interface. Non-linear editors can quickly create highly advanced virtual sets and augmented reality graphics thanks to its quick learning curve.
Qimera’s powerful production capabilities and stunning visual presentation qualities begin with the Qimera server, equipped with NVIDIA’s GeForce RTX 4090 GPU to produce AI-powered, data-driven real-time graphics with exceptional processing power. The solution builds in an array for other features that includes camera and talent tracking, lighting control with DMX, PTZ camera integration, a 3D assets library, and realistic graphics via Unreal Engine. Additionally, Qimera can adapt ENCO’s live captioning and text-to-speech technologies into its workflow, introducing opportunities to add synthetic voice to dynamic virtual productions.
