Why choose +VOCE
+VOCE is at the very core of Cedat85’s technology, it is the Company’s patented automatic speech recognition system, with text and audio synchronisation and advanced search capabilities.
End-to-end usable digital content
- +VOCE represents the most complete and sophisticated system capable of making any multimedia sequence containing speech comprehensible and immediately usable.
- The platform provides APIs that use speech recognition capabilities to produce transcripts of audio in real time.
- Cedat85’s automatic natural speech processing system automatically decodes the audio and transcribes the content for subsequent indexing.
- The service supports HTTP Representational State Transfer (REST) interfaces to transcribe speech from various languages and audio formats.
- The transcribed text is the basis for precise indexing of the audio-visual (or even the audio alone), enabling high-performance full-text searching. Thanks to the point & click system, which links each word to the millisecond of the video where it was pronounced, it is possible to guide the user exactly to the frame being searched for and to the exact point at which the word, name or topic of interest was cited.
- In case of large video archives, +VOCE is able to generate a structure directly from content indexing. The result is a dynamic content refinement interface that allows the user to easily navigate the audio-video archives, even if they are quite extensive.
- Thanks to +VOCE’s ability to structure contents natively unstructured, it will be possible to skim the audio-video according to their real content, using filters created ad hoc according to customer needs.
Available in over 20 languages.
Request a Demo
Fill the form and choose a date to organise your demo