Intelligent Voice Exhibit Production
As shown in the Media section below:
- The Intelligent Voice Player, with its optionally displayed auto-tag summary and auto-scrolling separated transcription, can be downloaded from Relativity as a standalone HTML file.
- A Web Video Text Track VTT file with split gap timings can also be produced from within both Relativity and from the downloaded HTML player.
- Channel separated and biometric speaker separated versions of the automatically transcribed Extracted Text are also available to produce.
The automatically transcribed text will track any change from one spoken language to another during the recording.
The default Split Gap timing separation between successive segments of text within the Web VTT, corresponding to which portions of a presented video should show what text as Closed Captioning, can be set to the nearest tenth of a second prior to production.
Text segments can then be edited prior to being used to caption a video presentation. This includes finessing individual start and end timestamps for segments of text to the millisecond.
The Web VTT file can be used as the basis for transcripts presented alongside the video playback, or be converted to other time-aligned, video-orientated presentation formats.
Intelligent Voice Exhibit Preparation
The Web VTT is initially produced as a custom .vtt mime type which can be opened and edited in any standard text editor or viewer such as Notepad or Word.
The Web VTT can be converted to other time-aligned, video-orientated presentation formats such as SubRip or TTML Timed Text Markup Language subtitling formats.
The Web VTT can also be converted into any recognised text file or document format such as .txt, .docx or .pdf, or into a line-by-line format such as .csv or .xlsx.
A transcript can also be presented in the preferred format alongside each audio or video file to be played, whether the starting point for the presented transcript had been a Web VTT, or the Extracted Text in either block, channel separated or speaker separated formats.
Additional production formats are available from processing direct on the Intelligent Voice server deployed to support RelativityOne and / or Relativity Server, whether deployed Edge on-prem, private cloud or partner hosted:
- US Federal Court Format Transcript Text Files
- XML
- SubRip subtitle file (SRT) with Word Confidence Scores
- Plus optional Concordance format .DAT Data Load File
Intelligent Voice Exhibit Presentation
The optimized video-aligned closed captioning, whether as a .vtt or format converted to .srt or .ttml, can be used to display the relevant transcribed text on-screen as the video is played.
For the list of exhibits, the actual playable duration of each media file is available, in both numeric and H:MM:SS formats, from dedicated document list columns in Relativity.
A private, generative AI narrative description can also be included as a column on the list of exhibits, providing a precis of each recording in the production set.
Intelligent Voice Pricing
The only cost from Intelligent Voice Limited is for the speech to text processing undertaken prior to producing.
If speech to text processing had already been undertaken for
Analytics or Search then the voice evidence production and presentation capabilities are available at no additional charge.
If speech to text is required specifically to enable redacted productions of media and / or text, a pre-processing billing assessment enables the cost to be determined to the cent prior to any processing.
Free use for approved Relativity
Justice for Change projects, leveraging the unique capabilities of Intelligent Voice and Relativity to positively impact racial and social justice in our communities.
Reach out to us with any questions you may have, or to arrange a quick walk through or to discuss next steps.