optional module

Speech to text

speech recognition over audio

The module allows to index the text contained in the clips as a metadata related to video and audio. Many times the signals do not have complementary information about the video like Closed Caption or Subtitles. For these cases, the transcription tool allows audio conversations to be used to extract the text as metadata and then allow searches or provide alerts for the appearance of keywords.

Transcription from audio to text

audit, production and monitoring

Deep learning

Learning engine that allows customized training

100% web operation

The configuration and operation is 100% Web. HTML5 It does not require plugins. Compatible with all standard shippers in the market

Search for words and names

Searches on audio visual content


English, Spanish, German, French, Indian, Chinese, Russian, Turkish, Vietnamese, Italian, Dutch, Catalan, Arabic, Greek, Farsi, Filipino, Ukrainian, Kazakh, Swedish, Japanese, Portuguese

Automatic transcription allows intelligent searches, either by identical or similar words, groups of words, or phrases.

It is a very powerful tool to audit media or politics. It can be used to know what they are saying about a brand, an entity or a person.

The search engine automatically takes you to the video fragment, so that you can quickly view and export the segment of interest.

In the search engine they can be combined with Station and date/time filters.

The search engine groups text fragments so that you can search for several words and see if the combination of those words appears at any time. Very useful to search for news where a person, or an organization is linked to a specific event, or a place or another person.

Searches can also be exported to CSV or XLS files as reports, and the system has a very powerful text indexing engine which allows for very fast searches with hours and hours of indexed content.

As you can see in the image on the left, the new “Crear Texto Avanzado” functionality allows generating the audio transcription to a text with punctuation marks, thus facilitating the user’s work.


Associated Products

products to which the speech to text additional module can be applied