Question 1

How does this skill keep my audio private?

Accepted Answer

The audio is transcribed entirely on your machine with faster-whisper and is never uploaded anywhere. The transcript text is then read by your AI agent to write the translation and summary, so it is processed by your agent’s model provider (for example, Anthropic for Claude Code) under their terms, like any other text in your chat. If the transcript itself is too sensitive for that, use only the CLI and read the transcript files yourself.

Question 2

Can this skill handle voice notes that switch between Arabic and English?

Accepted Answer

Yes. Whisper large-v3 handles Arabic with English words mixed in, but it often drops or garbles English terms and brand names in dialect speech. The skill doesn’t fix those words. It flags the unreliable segments, marks uncertain words with [?], and suggests what they probably say, so you know which parts to listen to again.

Question 3

What are the hardware and software requirements to run this skill?

Accepted Answer

Python 3.10+, ffmpeg, git, and an agent that can run shell commands on your machine (tested with Claude Code). Disk: about 3.5 GB (3.1 GB model plus Python packages), or about 4.5 GB with NVIDIA GPU support.

Question 4

Are the transcription models included in the initial download?

Accepted Answer

No. The skill includes the instructions and the CLI source code. The Whisper model (about 3.1 GB for large-v3, 1.5 GB for medium) is downloaded once on first use, only after you approve it, and then cached locally. After that, transcription runs fully offline.

Question 5

Do I need a high-end GPU to use the transcription feature?

Accepted Answer

No. On a modern laptop CPU it runs at about real time (a 2.5-minute note takes about 2 minutes). An NVIDIA GPU with CUDA 12 is about 6x faster (about 17 seconds). The skill uses the GPU automatically when available and falls back to the CPU.

Question 6

Does the skill provide both a transcript and a translation simultaneously?

Accepted Answer

Yes. You get the original transcript with timestamps (transcript_ar.txt) and a line-by-line English translation with [?] marks (transcript_en.txt), saved next to your audio file. In the chat you also get answers to your questions and a table of the least reliable segments.

Question 7

Which agents does it work with?

Accepted Answer

Any SKILL.md agent that can run shell commands on your machine should work, but it has only been tested with Claude Code on Windows 11.

Question 8

Does it work for languages other than Arabic?

Accepted Answer

Yes, for any language Whisper supports. Ask for the language (for example “it’s in English”), or let it detect the language automatically.

Time	Arabic (as transcribed)	English
00:00–00:04	السلام عليكم، كنت بحاول ادخل على البروفايل بتاعي	Hi, I was trying to get into my profile
00:04–00:11	بس الصبسكريبشن مش راضي يتجدد خالص من الايفون	But the subscription [?] won't renew at all from the iPhone
00:11–00:17	جربت افتح الابلكيشن كذا مرة ومفيش فايدة، حتى نزلت	I tried opening the app several times, no use. I even downloaded [?] (a word is missing here)
00:17–00:21	بس برضو نفس المشكلة	but it's still the same problem.

Time	Transcribed	Likely meaning
00:04	الصبسكريبشن	"subscription", an English word written phonetically
00:15–00:17	حتى نزلت …	A word is missing after "I even downloaded", possibly an app name. Worth listening to.

WhatsApp Voice Note Transcribe