Our technology is able to understand image content in several different manners. Image classification is useful for information retrieval and content categorization. For instance, visual sensitive content can be filtered by detecting terrorism, sex scenes and others relevant categories. Image segmentation and pattern recognition allows the automation of some manufacturing process, logos detection and recognition among others. For example, it can be applied to a quality process based on image inspection where manufactured components must be segmented and evaluated. Image captioning deals with the description of the image content to understand the action that represents the image. It is useful for monitoring some events as the detection of sign language interpretation.

Create automatic speech-to-text transcriptions from every audio and video format. We provide a hybrid-solution using off-the-shelf libraries and third party services to obtain the best speech transcription qualities. Main languages are spanish, catalan and english but it can be extended to more than 40 languages. Generate closed captioning using custom tools to enhance the punctuation and capitalization and export them to the most popular formats (srt, vtt, etc...). Synthesize speech from text using custom model voices or cloning the original voices. A service useful for voice over or dubbing video content to multiple languages.