Qencode has added Translations to its Speech-to-Text output, enabling video teams to transcribe spoken audio and receive localized subtitles and transcripts in more than 80 languages in one encoding job.

Video Intelligence, now available on Qencode, accelerates video processing by delivering insights across videos in seconds. Powered by TwelveLabs and integrated directly into the encoding pipeline, it reaches across video, audio, speech, and on-screen text, returning timestamped results across five modes: description, categorization, moderation, custom, and search.

Content Operations teams are challenged by the rapid influx of AI-generated uploads, complicating moderation efforts. The newly launched AI Detection tool allows real-time verdicts on uploads, enhancing moderation efficiency and enabling proactive management of user-generated content before viewer complaints arise.

Qencode, a video processing platform, has joined the Alliance for Open Media (AOMedia) as a Promoter Member to contribute to multiple working groups. With AV1’s growing support and AV2 in draft, Qencode aims to enhance practical adoption and interoperability of these codecs, promoting open standards for accessible video technology development.