Audimus Server – Offilne Transcription

Introducing Audimus.Sever,

The Offline transcription platform for TV Broadcasters, Media subtitling, Content and Post-production.

Audimus.Server creates acoustic and linguistic metadata from/for the audio/video contents by combining the results of automatic language and speaker identification tools with the transcriptions produced by a cutting edge speech recognizer, which are later enriched with NLP text annotations.

The system supports the most commonly used subtitle (closed captioning) formats, bringing about the possibility of quickly creating accurate transcriptions and speeding up translation workflows.

Product Specs