Overtone
Smart video captions that adapt to every screen shape from a single file
Visit website →About
Overtone is a new caption format with a video player and CLI tool. It stores every spoken word once with its time and speaker, then cuts lines separately for each screen shape: 16:9, 9:16 or any ratio you define. The player shows the cut closest to the picture shape.
It does not just rewrap lines — it follows real reading rules: lines avoid ending on weak words, names and numbers stay together, each speaker gets their own caption, and pauses become breaks. In a test on three English clips, only 0.3 percent of Overtone breaks ended on a weak word versus 29 percent when filling lines to the limit.
Overtone is open-source under the MIT license. The CLI can re-cut existing SRT files or create new captions from audio using OpenAI, Azure AI Speech and ElevenLabs. Cost is about $0.023 per audio minute.
AI-assisted draft, human-reviewed before publishing — see how we choose & review tools.
Why we picked it
Traditional captions are cut once for one screen. Overtone solves a real problem: the same video on YouTube and TikTok with perfect captions for each. The 0.3 percent versus 29 percent weak-break benchmark speaks for itself.