音频转文本整理稿(本地部署版):本地 ASR 与中文整理稿输出
介绍 SkillHub 社区技能「音频转文本整理稿(本地部署版)」(@user_695efa3d/transcript-organizer,v1.0.0)。技能接收音视频、播客链接、字幕或已有转写稿,在本机用 faster-whisper 或 mlx-whisper 完成 ASR,经清洗整理后输出分享式提纯版中文原文到本地 .txt,无需 API Key。文章说明核心能力、SkillHub CLI 安装路径(含 Cursor 等 skills 目录)及典型对话用法,并列出适用场景与本地部署注意点。
Read MoreB站文字稿:用 Agent Skill 把 bilibili 视频转成带时间戳的文字稿
介绍 SkillHub 社区 Skill「B站文字稿-提取B站视频为文字稿」(@user_0b65fce7/bilibili-txt,v1.0.0)。面向从 bilibili.com 视频 URL 提取完整文字稿、字幕与语音转写需求,支持拉取音频并用 Whisper 做中文识别,输出带时间戳的结构化文稿;标签 requires_api_key=false。文章说明 Skill 定位、核心能力、通过 skillhub CLI 或安装文档写入 Cursor/Claude Code/Codex 等 skills 目录的方式,以及「提取B站」「B站文字稿」等触发用法与合规注意。
Read MoreOpenai Whisper Skill:用 Whisper CLI 本地语音转文字
Openai Whisper 是 SkillHub 上的 Agent Skill(@clawhub_steipete/openai-whisper,v1.0.0),指导 Agent 调用本机 Whisper CLI 完成语音转文字,标签 requires_api_key=false。文章说明其定位、核心能力、通过 skillhub install 安装到 Cursor 等 skills 目录的方法,以及上游提供的转写与翻译示例命令。适合 design-media 场景下处理本地音视频素材的开发者;需自行安装 whisper 并承担模型下载与算力成本。
Read More抖音视频提取文案:本地 Playwright + Whisper 把分享链接转成文字
介绍 SkillHub 社区 Skill「抖音视频提取文案」(@user_6a36b82b/douyin-transcribe-lz,v1.1.1)。当用户提供 v.douyin.com、douyin.com、iesdouyin.com 链接或整段分享口令,并提出提取文案、视频转文字、语音转录或「这个视频说了什么」等意图时,Agent 应启用该 Skill。底层用 Playwright 绕过登录墙捕获视频,Whisper medium 本地转录中文,无需云端 API,requires_api_key=false。文中说明 skillhub CLI 安装命令、各客户端 skills 目录及典型对话示例。
Read More视频剪辑神器:把本地视频后期交给 Agent Skill 编排
介绍 SkillHub 社区 Skill「视频剪辑神器」(@user_176cb31c/video-auto-editor-skill,v1.0.0)。它面向录屏后期、直播回放切片与短视频批量处理,支持本地截取、Whisper 字幕生成与嵌入、拼接、转码缩放、水印、音频提取替换、直播切片及 JSON 工作流编排,且无需 API Key。文章说明其定位与已核实功能,并给出 SkillHub 官方安装提示与 skillhub CLI 安装命令及 Cursor、Claude Code、Codex 等 skills 目录示例;典型用法需以安装后的 SKILL.md 为准。
Read MoreMeeting Notes Assistant:本地 Whisper 转写与结构化会议纪要
Meeting Notes Assistant 是 SkillHub 社区 Skill @user_cffec473/meeting-notes-assistant(v1.0.0,office-efficiency)。使用本地 Whisper 离线转写会议录音,生成含时间、议题、结论、待办与关键词的结构化纪要,并提取 Action Items,支持 Word、PDF、邮件输出。可通过「整理会议纪要」「生成会议纪要」「录音转纪要」等关键词在 Agent 中触发;安装需 skillhub CLI 并指定各客户端 skills 目录。标签含 requires_api_key,使用前按 Skill 说明配置。
Read Moredsh-voice: A Local Voice Input Plugin for DeepSeek Harness
dsh-voice is a DeepSeek Harness plugin that provides local speech-to-text (STT) for the Web UI and TUI. It uses the host-side ONNX-based Whisper service and integrates the microphone in the browser, enabling privacy-safe voice input without external binaries. To install, add it to a DSH Profile; configuration is optional. It supports downloading various Whisper models from Hugging Face. Note that TUI mode depends on system recording tools, while in Web mode audio is recorded locally and transferred over HTTP.
Read Moredsh-voice-input: System-Level Voice Input
`dsh-voice-input` is a plugin for DeepSeek Harness, designed to enable global voice transcription in non-plugin environments. It leverages a local Whisper model to transcribe speech into text in real time via hotkeys and paste it at the cursor position. Installation requires running DSH with administrator privileges. Main features include holding F2 for voice transcription, pressing F3 to record audio only, and managing the history through the system tray. The plugin supports configuring the recognition mode, language, and device, and requires downloading approximately 2.5GB of dependencies and models upon first use.
Read MoreFine-tuning Whisper Speech Recognition Model and Accelerating Inference
Thank you for providing the detailed project description. To help more people understand and use your project, I will summarize and optimize some key information and steps: ### Project Overview This project aims to deploy a fine-tuned Whisper model to Windows desktop applications, Android APKs, and web platforms to achieve speech-to-text functionality. ### Main Steps #### Model Format Conversion 1. Clone the Whisper native code repository: ```bash git clone https://git
Read More