Accurate Real-Time Speech-to-Text Processing
As a business where customer collaboration is key to our product development Screen actively encourages its customers to challenge the limits of both language accuracy and language support.
If a language is not supported and you are able to provide material and accurate transcription then we’d be more than happy to discuss potentially adding the language to the bouquet supported today.
As part of the process of creating subtitles from the Speech Engine, results are also recorded to a TTML for archive, compliance, repurposing and metadata harvesting workflows.
In the demanding world of re-speaking VoCaption is considered a complimentary product to existing workflows where it potentially increases productivity at a reduced cost.
In a newsroom or any other re-speaking scenario that would traditionally require a team of re-speakers to operate, efficiency could be achieved from switching between the re-speaker and VoCaption. During periods of presenter/newsreader speech VoCaption could process the content and during OB/VT the re-speaker could take over.
This would allow the re-speaker to take more frequent breaks, and being more rested, would ensure a higher quality of output and a reduction in errors. Enabling subtitling for audiences within governmental, educational and military institutions, as well as meetings and presentations – VoCaption also extends accessibility far beyond the traditional broadcast sector.
– Automatic failover to Speech when integrated with our market-leading Polistream platform.
-Processes audio content from line-input, AES or directly from SDI/HD-SDI/3G-SDI signal.
-Language output support is limited only to the respective Speech Engines capabilities.
-When used in conjunction with Polistream VoCaption enables the widest range of linear broadcast and OTT delivery mechanisms available in the market today.