Audio local
给 Claude Code + DeepSeek 装上眼睛和耳朵：本地多模态 Skills 套装，支持图片识别/OCR（Ollama minicpm-v）和语音转文字（faster-whisper large-v3-turbo），纯本地运行无需云服务
npx -y skills add jk241282/-deepseek-skills --skill audio-localAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
当用户发送音频文件或要求语音转文字、音频转录、录音识别时使用此 skill。使用本地 faster-whisper large-v3-turbo 进行语音识别。转录完成后，由 Claude 直接对文本进行总结、分析、翻译等后续处理。触发场景：用户上传音频/录音、要求语音转文字、会议转录、提取音频内容等。
SKILL.md
1.5 KB, 411 tokens by cl100k_base, as published. Nobody here has run it
本地语音转文字
管线
音频 → faster-whisper(转录) → 原文 → Claude 后续处理
转录由本地模型完成，文字结果的总结/分析/翻译由 Claude 直接处理，无需再调 Ollama。
执行步骤
1. 确认音频路径
获取音频文件绝对路径。支持格式：mp3, wav, m4a, ogg, flac, webm。
2. 执行转录
python "<skill目录>/scripts/transcribe.py" "<音频路径>" <语言>
- 语言默认
zh，英文音频用en - 模型路径可通过环境变量
WHISPER_MODEL_PATH设置，默认为~/models/faster-whisper-large-v3-turbo - 输出纯文本原文
3. 后续处理
拿到转录原文后，根据用户指令直接处理：
- 用户要求"总结" → Claude 直接总结原文
- 用户要求"翻译" → Claude 直接翻译原文
- 用户要求"提取要点" → Claude 直接提取
- 用户只说"转文字" → 呈现原文即可
故障排查
- 模型未找到: 检查
WHISPER_MODEL_PATH环境变量或~/models/faster-whisper-large-v3-turbo/目录 - 转录为空: 检查音频是否有效，语言代码是否正确
Gives 0 of the 12 instructions most video audio skills give in 411 tokens
Counted across 622 of the 795 authors here whose files we hold, read 2026-08-07
- read individual rule files for detailed explanationsin 21 of 622, across 10 files
- render final videoin 13 of 622, across 6 files
- Use WAV PCM 16kHz mono audio formatin 12 of 622, across 3 files
- Use this skill when dealing with Remotion codein 11 of 622, across 4 files
- save generated audio to a WAV filein 11 of 622, across 4 files
- handle conversion errors gracefullyin 10 of 622, across 6 files
- add captions to videos alwaysin 10 of 622, across 4 files
- generate music from text descriptions using MusicGenin 9 of 622, across 2 files
- do not skip pipeline layersin 9 of 622, across 3 files
- do not make one tool do everythingin 9 of 622, across 3 files
- use azure document intelligence for complex pdfsin 9 of 622, across 4 files
- never ask the user to paste their full API keyin 9 of 622, across 3 files
Said here and by no other author read
- Get the absolute path of the audio file
- Set transcription language to zh by default
- Set transcription language to en for English audio
- Process transcription text directly per user request
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.