arabic-voice
Captures an Arab creator's real speaking voice (dialect, rhythm, signature phrases, code-switching) into a reusable Voice Card, and rewrites stiff or AI-sounding Arabic into natural spoken Arabic. Use before writing any Arabic script, caption, or post; when the user says "اكتب بأسلوبي", "خليه بالمصري/بالخليجي", "الكلام ده شكله AI", "عايزه طبيعي", or shares past videos/captions as a voice reference.
Original · translation is not supported for this source languageTarget: Software development & testing. Automatically collected · unverified.
Excerpt from the author’s documentation
Extracted from a fixed version of SKILL.md in its original language. This is the author’s documentation; installation, compatibility and runtime results have not been verified by this site.
Read the original text
Topics in the source
- Arabic Voice
- 1. Build the Voice Card
- 2. Dialect cheat-sheet (use the creator's column only, never mix dialects)
- 3. De-AI rules for Arabic
- 4. Rewrite procedure
- 5. Self-check
Most AI Arabic sounds like a translated press release: formal (فصحى), long sentences, and words nobody says out loud. Your job is to make text sound like this specific creator talking to camera. From 1–3 samples (transcripts, captions, posts, or a description), fill in: If there are no samples, ask for one. If the user wants to skip, default to friendly-smart in the dialect they wrote to you in, and say that it's a default. | Meaning | Egyptian | Khaleeji (Saudi/Gulf) | Levantine | MSA-light | |---|---|---|---|---| | what | إيه | وش / ايش | شو | ماذا → ما | | want | عايز | أبغى / ودي | بدي | أريد | | now | دلوقتي | الحين | هلق | الآن | | look/listen | بص / اسمع | شوف / اسمع | شوف / اسمع | انظر | | very | أوي / جدًا | مرّة / وايد | كتير | جدًا | | like this | كده | كذا | هيك | هكذا | | why | ليه | ليش | ليش | لماذا | | good/ok | تمام / ماشي | زين / تمام | منيح / تمام | جيد | MSA-light means modern spoken فصحى: short sentences and no archaic connectors (إذ، حيث إن، ومن ثم، علاوة على ذلك). Remove or replace these: Formal openers: «في هذا الفيديو سوف نتحدث عن»، «مرحبًا بكم أعزائي المشاهدين»، «دعونا نتعرف على». Stacked connectors: «بالإضافة إلى ذلك»، «علاوة على ذلك»، «من ناحية أخرى»، «و
This is an excerpt. Refer to the complete source and its current requirements.
- Source repository
- alfaris/full-production-studio
- Source file
- originals/arabic-voice/SKILL.md
- Fixed revision
- 223f74cc6dceb4c16858c4d58b5d066e7c5eeb83
Requirements
- Only the author’s Skill metadata is included. Read the full instructions to check dependencies, licensing and conditions of use.
A small first task
先阅读原作者说明，再决定是否在自己的 AI 工具中使用。
Instructions for your AI tool
- Claude Desktop: resource-specific guide not available yet
- Claude Code: resource-specific guide not available yet
- Cursor: resource-specific guide not available yet
- Codex: resource-specific guide not available yet
Author documentation is not live verification by this site. Without evidence, we do not mark a resource as compatible, safe or free.
Sources and evidence
This record was collected automatically. Its documentation, suitability and runtime behavior have not been manually verified.
Author: alfaris/full-production-studio · original repository metadata. Documentation review: Not reviewed. Last source check: 2026-11-10T12:01:33.688Z.
Categories are inferred from names, descriptions and paths. They do not establish compatibility.
License and attribution
MIT. Third-party content and copyright remain with their authors. Refer to the original license and terms.
Original license ↗Synchronization, copying and user-reported success do not mark a resource as runtime-tested.
Limitations and notes
- Collecting metadata does not mean this site has installed, adapted, runtime-tested or security-reviewed the resource.