Qwenasr logo

Qwenasr

Community
dseditor
qwenasr

用本機「聲音辨識小工具」(QwenASR) 把音訊/影片轉成字幕,並在取得逐字稿後做校正、摘要或改寫。當使用者說「轉錄」「上字幕」「聽打」「這段錄音講什麼」「幫我做逐字稿」「校正字幕」「摘要這段音檔」,或給了 .mp3/.wav/.m4a/.mp4 等檔案要求處理內容時使用。全程在本機執行,音訊不外傳。

Overview

Publisherdseditor
RepositoryQwenASRMiniTool
Skill nameqwenasr
Stars
570
Forks
79
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by dseditor on GitHub. Read the source before you install it.

Installation

Install the Qwenasr AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/dseditor/QwenASRMiniTool/tree/main/.claude/skills/qwenasr
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/dseditor/QwenASRMiniTool.git /tmp/QwenASRMiniTool
mkdir -p .claude/skills
cp -r /tmp/QwenASRMiniTool/.claude/skills/qwenasr .claude/skills/qwenasr
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Qwenasr in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Qwenasr on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Qwenasr is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

QwenASR — 本機語音辨識(Agent 用法)

QwenASR-WebView.exe 帶子命令執行時是無頭 CLI:不開視窗、跑完即退、 stdout 只有結果、進度走 stderr。適合直接在 Bash 工具裡呼叫。

找到執行檔

依序尋找,找到第一個就用(請用絕對路徑呼叫):

  1. 使用者明講的路徑
  2. F:\AIStudio\QwenASR\dist2\QwenASR-WebView\QwenASR-WebView.exe
  3. 開發環境(沒有 EXE 時):F:\AIStudio\QwenASR\venv\Scripts\python.exe F:\AIStudio\QwenASR\app_webview.py

找不到就問使用者 EXE 在哪,不要自己去裝別的 ASR 工具。

先確認狀態

bash
"<EXE>" status --json

回傳已選核心、模型是否就緒、加速版本。selectedReady:false 代表模型還沒下載—— 第一次轉錄會自動下載(1~2.5 GB,需數分鐘),先告知使用者再繼續。

轉錄

bash
"<EXE>" transcribe "D:\path\audio.mp3" --json

stdout 是一份 JSON:

json
{"input":"...","ok":true,"srtPath":"...\\subtitles\\audio.srt",
 "segments":[{"i":1,"start":0.48,"end":1.84,"text":"再看立法院的質詢"}, ...],
 "text":"整段連續逐字稿"}

常用選項:

選項說明
-l Chinese / Japanese / English指定語言(留空=自動偵測;已知語言時指定較準)
--profile zh|tea|ja|twmix依用途換模型,只影響這次執行,不會改到使用者 GUI 的設定
--hint "人名、術語、背景說明"提示詞,能明顯改善專有名詞
--diarize [--speakers N]說話者分離(segments 會多 speaker 欄位)
-o out.srt / -f srt|txt|json指定輸出檔與格式(僅單一輸入時有效)

--profile 選哪個(不確定就用預設,別亂換):

  • zh 中文標準 — 一般情況的預設,斷句標點最完整
  • tea 台灣國語 — 訪談/質詢/講座等乾淨人聲,原生輸出繁體 ⚠️ 背景配樂較重的段落或歌曲可能整段無輸出,音樂類素材不要用它
  • ja 日本語 — 日語/動漫語音
  • twmix 國台語混合 — 速度極快,但不輸出標點

多檔:transcribe a.mp3 b.mp3 c.mp3 --json → {"results":[...]}。

校正字幕(重要:時間軸不可碰)

流程是三步,中間那步才是你做的事:

bash
# ① 轉錄並存成 JSON
"<EXE>" transcribe "audio.mp3" -o work.json -f json --json > result.json

# ② 你讀 work.json,只改每個物件的 "text",存成 fixed.json
#    絕對不要改 i / start / end,也不要增刪段落

# ③ 用原始檔當時間軸基準寫回 SRT
"<EXE>" apply fixed.json --base work.json -o final.srt

--base 會以原始檔的時間軸為準,只從你的檔案取 text 依 i 對應回填 —— 就算你不小心動到時間,也會被基準檔蓋回去。校正時一律加 --base。

校正時該做與不該做:

  • ✅ 錯字、同音字、專有名詞、人名、公司名、術語
  • ✅ 明顯的語音誤判(「修醉」→「修碎」之類,依上下文判斷)
  • ❌ 不要潤稿、不要改語氣、不要刪贅字 —— 除非使用者明確要求
  • ❌ 不要合併或拆分段落(會與時間軸脫節)

摘要 / 改寫

EXE 只負責交出逐字稿,摘要是你自己做。用 --json 拿 text 欄位 (整段連續逐字稿)或 segments(要引用時間點時用)直接處理即可, 不需要任何額外命令。要標時間點時引用 start,格式化成 mm:ss 給使用者。

注意事項

  • 第一次執行會下載模型(1~2.5 GB)。長音檔轉錄可能數分鐘 —— 用背景執行 或把逾時放寬,不要中途重試(會重跑整個檔案)。
  • stdout 是乾淨 JSON;載入與進度訊息都在 stderr。解析前不需要清洗。
  • 退出碼:0 成功/1 轉錄失敗/2 參數錯誤/130 中斷。
  • 影片檔(mp4/mkv/…)可直接餵,會自動抽音軌(首次需下載 ffmpeg)。
  • 產出的 SRT 預設落在 EXE 旁的 subtitles\,路徑在 srtPath。
  • 「未產生字幕(未偵測到人聲)」通常是素材與模型不合(例如用 tea 轉歌曲),改用 --profile zh 重試。

查可用模型

bash
"<EXE>" profiles --json     # 含本機硬體判斷與各 profile 是否已下載

Frequently asked questions

What does the Qwenasr AI skill do?

用本機「聲音辨識小工具」(QwenASR) 把音訊/影片轉成字幕,並在取得逐字稿後做校正、摘要或改寫。當使用者說「轉錄」「上字幕」「聽打」「這段錄音講什麼」「幫我做逐字稿」「校正字幕」「摘要這段音檔」,或給了 .mp3/.wav/.m4a/.mp4 等檔案要求處理內容時使用。全程在本機執行,音訊不外傳。

Why use Qwenasr on TypingMind?

Because you install it once and use it with any model. Qwenasr is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Qwenasr in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dseditor/QwenASRMiniTool/tree/main/.claude/skills/qwenasr. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Qwenasr?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Qwenasr?

As many as you like. As long as a model supports skills, you can use Qwenasr with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Qwenasr AI skill free?

It is published on GitHub by dseditor. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇