Overview
Highlights: fully local processing and storage, no network dependency, no GPU dependency, very fast on CPU. Features: Fast on CPU — i5-11400H: 30min of audio finishes in 1min (a five-year-old CPU); i5-4210m: 30min of audio finishes in 3min (a ten-year-old CPU). Real-time recognition supports mic, system audio, or both streams at once. Supports subtitle and voice-input modes, plus synced translation (via a self-hosted LLM; HY-MT1.5-1.8B recommended, extremely fast). Recognize audio/video files: supports mainstream formats. Built-in FFmpeg can convert many formats. Speaker management: built-in speaker management can assign a model to each speaker for recognition. Powerful edit and search: custom dictionaries; auto post-process with dictionary content; manual edit; click recognized text to jump to the matching audio; batch delete and replace; global search. Local LLM support: built-in ollama interface with one-click start and one-click processing.
Connected profiles
More Productivity products
Sources · 0Sources & provenance
English text is maintained separately from the original record. Consult the original source before citing a fact.
No source links are available for this profile.
Original source text
Names may use phonetic renderings when no English name is supplied. The original wording is retained below.
功能亮点完全本地处理与存储，不依赖网络不依赖GPU，CPU速度飞快功能介绍CPU飞快i5-11400H：30min的音频 1min就能处理完（五年前的CPU）i5-4210m：30min的音频 3min就能处理完（十年前的CPU）实时识别支持识别麦克风、系统声音或者双路同时识别。支持字幕和语音输入模式，支持同步翻译（通过自部署LLM模型，推荐HY-MT1.5-1.8B，速度极快）识别音视频文件支持主流音视频文件。内置FFMpeg处理，可以转换各种格式。说话人管理内置说话人管理可以为每个说话人指定模型进行识别强大的编辑与搜索功能支持自定义词典。自动调用词典内容进行后处理。支持手动编辑，点击识别文本自动跳转到对应音频。支持批量删除与替换支持全局搜索本地LLM支持内置ollama接口，支持一键启动，一键处理。