AUDIMUS.MEDIA produces subtitles automatically and in real time on live contents.
How live subtitling works:
CAPTURING: AUDIMUS.MEDIA captures feeds from any pre-existing or produced audio or video' sources (digital or analog).
PROCESSING: Through automatic speech recognition, AUDIMUS.MEDIA produces subtitles automatically with a very small latency time, identifying all pivots and different speakers.
DELIVERING: The system will send the subtitles to a subtitling/teletext encoder, in less than 3-4 seconds’ word by word. The output text is standardised, formatted and optimized for a wide range of encoders.
Languages: Different language models are provided with specific themes each (e.g. news, sports). These are trained with large amounts of audio and text, where the total volume of vocabulary exceeds 200,000 words. Even more, it is possible to adjust the phonetic transcriptions to adapt models to local language.
Features
Languages: Different language models are provided with specific themes each (e.g. news, sports). These are trained with large amounts of audio and text, where the total volume of vocabulary exceeds 200,000 words. Even more, it is possible to adjust the phonetic transcriptions to adapt models to local language.
Metadata: AUDIMUS.MEDIA allows the addition of metadata automatically to the content to be broadcast.
Language Coverage
English
(Latin),
Portuguese
(Latin),
Spanish; Castilian
(Latin),
French
(Latin),
German
(Latin),
Italian
(Latin),
Basque
(Latin)
