Metadata is essential to find the video you need, especially in the newsroom. Etere facilitates automatic metadata tagging, including Face Recognition, Speech-to-text and OCR in video images.
Etere allows different automatic metadata tagging, including,
Etere Ecosystem integrates next-generation AI technology into its Media Asset Management (MAM) solution and expands its search parameters to include facial recognition. Using image recognition, Etere analyzes individual scenes in the media library and produces a list of matches in seconds. The advanced facial recognition technology works even for media files with low lighting and obscure angles.
Etere Subtitles Tool for Closed Captions supports Google Cloud Speech-to-Text, which includes support for up to 120 languages, with each language specified within a recognition request’s language code parameters.
Each language code parameter includes a BCP-47 identifier tag that identifies the language and region/country of the language. With the upgrade, operators can instantly convert audio to closed caption text to support a global audience base. Etere can support voice-to-text commands, real-time streaming and the processing of voice commands/audio transcription from call centres. In addition, Etere is also able to process pre-recorded audio using Google’s machine-learning technology.
- OCR in video images
Optical Character Recognition (OCR) technology recognizes text within a digital image. It is commonly used to identify text in scanned documents and photos. With OCR technology integration, users of Etere can convert a physical paper document or an image into an accessible electronic version with text.
Contact us for a personalized consultation to explore how Etere AI technology can enhance your operational efficiencies.