Able to process up to 8 hours of spoken audio in 1 hour, whether originating from a life feed or pre-recorded signal, our Speech-to-Text technology stands out due to its accuracy and unparalleled performance. It supports most of the European and Asian languages, including various sorts of English and Spanish, and can process all the major file types. In addition to that, the overall accuracy can be easily improved by feeding the system a text document with the new words or expressions.

Characteristics:

• Automated video and audio time-stamped transcription.
• Live input feed processing and speaker recognition.
• Support for the following languages: Arabic, English (various sorts), Spanish (various sorts), Farsi, Russian, Danish, Swedish, Catalan, Mandarin, Japanese, Korean, German, Dutch, Portuguese, Turkish, Greek, French, and Italian.
• Support for the following file types: AVI, FLV, WMA, WMV, WAV, AU, MPEG, MPEG2, VOX, OGG, MP3.
• Process 8 hours of audio in 1 hr.
• Accuracy improvement by feeding the system a text document with the new words or expressions.