Discussions

I am testing localization for very short two-person clips. The source is a two-photo AI rap video workflow that generates original English vocals in 5, 10, or 15 second scenes. Each line is assigned to one of two speakers and aligned to a beat window.

Hi, we run ClipMelody , a small tool that identifies the song playing in a TikTok, Reel or Short. Users keep asking for the lyrics in their own language next to the result, so we are looking at a translation API. Lyrics usually come as short line-by-line blocks of 2 to 6 words. Is it better to send each song as one document with line breaks kept, or as separate segments so line alignment is preserved? Also, is there a recommended way to flag text that should stay untranslated, such as artist names and song titles?

Hi, I'm working on a research project where we collect public comments from TikTok and YouTube videos in several languages. We export them to CSV with Comment Viewer (one row per comment, columns for author, text, likes, date and parent reply id), and I'd like to send only the text column through the MotaWord API for translation into English.

Hi team, we review a lot of short vertical videos (mostly TikTok stories we save with TikViewer before they expire) and need their captions translated into 4-5 languages.

We produce short video ads automatically and need to localize them into several languages. Looking for the best workflow to translate on-screen text and voiceover scripts at scale. The tool we build is https://ravvi.ai and localization is our next step. How do teams handle multilingual video subtitles via API?