Overtone ships transcription correction and multi-aspect-ratio subtitles
What happened
On October 30, Hacker News' front page covered Overtone, a subtitle tool. It stores word-level timings and speaker info in a .overtone.json file and splits subtitles per aspect ratio, with a CLI and a video.js plugin. Existing SRT or WebVTT subtitles can be re-split offline. For audio and video transcription it defaults to OpenAI plus Azure AI Speech and uses an LLM for correction. It also runs locally via whisper.cpp and Ollama.
Written by AI from the coverage · updated 1 hour ago
Coverage
Follow the reports to see the story from different sides.
- Hacker News front pageShow HN: Overtone – Transcribe, correct and cut captions for any screen shape
Overtone 用一个 .overtone.json 文件保存逐词时间和说话人信息，并为不同画幅分别切分字幕，提供 CLI 和 video.js 插件。已有 SRT 或 WebVTT 可离线重新切分；音视频转录默认结合 OpenAI 与 Azure AI Speech，使用 LLM 纠错，也支持通过 whisper.cpp 和 Ollama 本地运行。
Heat over time
Not enough continuous observations to draw a trend yet.