UalterSound arrives, the AI ​​platform that converts speeches into texts, allows segmenting the analysis and creating pieces to share on networks

What will the world be like in the future? There is no single answer to the question, but one thing is certain: artificial intelligence will be decisive in its functioning, and will mark a turning point that goes beyond simple technological evolution.

Immersed in this reality, the media industry is closely following the development of AI and its potential uses. Clarion, Like other major news platforms in the world, it does so with curiosity but with conviction: AI will never replace journalists in producing original, creative and therefore unique content.

With this idea as a starting point, it is clear that it is imperative to move forward in experimentation and venture optimistically into the future, in the search to obtain the greatest benefits from new technologies.

On that path, last year Clarion was a pioneer in integrating its digital platform Walteran artificial intelligence reading assistant that offers a summary, highlights, data, a glossary, and questions and answers for each note to help break down the text.

But, as it could not be otherwise, Walter evolved, and today Clarion Take a step further and add WalterSoundan Artificial Intelligence platform that converts oral speeches into text, analyzes them and publishes an interactive version.

UalterSound allows you to read the words synchronized with the audio, and interact with any part of the text, jumping between paragraphs or topics.

What other features does it offer? After transforming speech into text, it analyzes it with Artificial Intelligence to create three modules that facilitate the extraction of information.

  • Index. It presents a thematic index that separates the contents of a speech into chapters. Within each chapter, the user will find the exact sentences, which can not only be read, but also listened to again.
  • Data module. If during the speech the speaker names data and figures, these numbers are identified to create an ordered table in which they can be individualized for analysis, in addition to accessing the audio fragment in which the speaker expressed the numbers.
  • Index of names. All those mentioned are presented in an interactive list arranged alphabetically. Clicking on the names displays the paragraphs in which they were cited.

In addition, of the most significant phrases identified by AI, The platform produces videos from audio over animated textsThe goal is to make it easy for users to share these videos or the fragments they deem appropriate on their social networks.

Oral speeches can address multiple topics in a single presentation, which gives them varying complexity. In addition to the usual analysis and interpretations offered by the press, and which Clarion will continue to produce, UalterSound adds the alternative of a different experience, offering the reader the possibility of reading linearly or exploring the content from different points of view, such as topics, data and names.

Many speeches are of great public interest. The words of a president or leaders with high responsibilities contain concepts that can affect the whole of society. On social media, users cut out fragments and post them to support or criticize the statements.

WalterSound will make the task easier by generating automatic text videos with the most prominent phrases. In an average exposure, The new tool will offer around 20 to 25 key quote videos. The number may vary for longer or shorter speeches.

The initiative, as always, responds to the vocation of providing the reader with a service that complements the informative reading, opinions and analysis that Clarion has been offering for 79 years.

By Editor

Leave a Reply