Faster Whisper

Local speech-to-text using faster-whisper. 4-6x faster than OpenAI Whisper with identical accuracy; GPU acceleration enables ~20x realtime transcription. SRT/VTT/TTML/CSV subtitles, speaker diarization, URL/YouTube input, batch processing with ETA, transcript search, chapter detection, per-file language map.

10 stars 4 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add ThePlasmak/faster-whisper --skill faster-whisper

Manual install

git clone --depth 1 https://github.com/ThePlasmak/faster-whisper.git /tmp/faster-whisper
mkdir -p ~/.claude/skills
cp -r /tmp/faster-whisper/. ~/.claude/skills/faster-whisper

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Faster Whisper

Local speech-to-text using faster-whisper — a CTranslate2 reimplementation of OpenAI's Whisper that runs **4-6x faster** with identical accuracy. With GPU acceleration, expect **~20x realtime** transcription (a 10-minute audio file in ~30 seconds).

## When to Use

Use this skill when you need to:

- **Transcribe audio/video files** — meetings, interviews, podcasts, lectures, YouTube videos
- **Generate subtitles** — SRT, VTT, ASS, LRC, or TTML broadcast-standard subtitles
- **Identify speakers** — diarization labels who said what (`--diarize`)
- **Transcribe from URLs** — YouTube links and direct audio URLs (auto-downloads via yt-dlp)
- **Transcribe podcast feeds** — `--rss <feed-url>` fetches and transcribes episodes
- **Batch process files** — glob patterns, directories, skip-existing support; ETA shown automatically
- **Convert speech to text locally** — no API costs, works offline (after model download)
- **Translate to English** — translate any language to English with `--translate`
- **Do multilingual transcription** — supports 99+ languages with auto-detection
- **Transcribe a batch of files in different languages** — `--language-map` assigns a different language per file
- **Transcribe multilingual audio** — `--multilingual` for mixed-language audio
- **Transcribe audio with specific terms** — use `--initial-prompt` for jargon-heavy content or any other terms to look out for

Read the full skill on GitHub

Details

Skill name: faster-whisper
Repository: ThePlasmak/faster-whisper
License: MIT
Repo updated: 22 February 2026

FAQ

What does the Faster Whisper skill do?

How do I install the Faster Whisper skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add ThePlasmak/faster-whisper --skill faster-whisper. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Faster Whisper popular?

It lives in ThePlasmak/faster-whisper, which has 10 GitHub stars and 4 forks.

Related skills

Poster Grid Inspector

Ygria/poster-grid-inspector

Analyze a poster or layout design image to detect its underlying grid system and export grid guide overlays. Use when the user wants to (1) identify the layout grid of a poster/design image (Swiss modular, N-column, asymmetric, baseline, golden ratio, rule of thirds, diagonal, radial, freeform, etc.), (2) get detected layout elements, keylines, and alignment notes, or (3) export the detected grid as an SVG overlay file or CSS Grid / Tailwind code. By default, use the host model's native multimodal vision capability; do not upload the image or call an external API.

Images, Video & Audio

Extract Youtube Transcript

Rtemm/claude-skills

Use this skill when the user wants to extract audio from a YouTube video and transcribe it. Triggers include: 'extract transcript from youtube', 'transcribe this video', 'get transcript from YouTube', 'extract audio and transcribe', or any message that includes a YouTube URL and asks for a transcript or transcription.

Images, Video & Audio

Procedural Landscapes

CK42BB/procedural-landscapes-threejs

Generate procedural 3D landscapes and terrain in Three.js using WebGPU compute shaders with automatic WebGL2 fallback. Covers heightmap generation via FBM noise, ridged multifractal, and domain warping; chunked LOD terrain meshes; slope-based multi-material texturing; procedural water planes; atmospheric sky rendering; and instanced vegetation scattering. Use when building terrain generators, open-world environments, landscape visualizers, flight simulators, or any 3D scene requiring procedural ground surfaces. Triggers: "procedural terrain", "landscape generator", "heightmap", "terrain mesh",

Images, Video & Audio

Patent Filing Qc

LeonardHope/Claude-Skill-for-Patent-Filing-Quality-Control

Comprehensive quality control for U.S. patent application filing documents. Use when the user asks to QC, check, validate, or review patent filing documents before submission to the USPTO. Performs 70+ automated and manual checks across specification, drawings, ADS, declaration, assignment, and power of attorney documents. Detects cross-document inconsistencies, formatting issues, missing required fields, and common errors.

Images, Video & Audio

Video to Claude

rohunvora/video-to-claude

Analyze videos with Gemini and get build instructions for Claude. Supports YouTube URLs, GIFs, screen recordings, and local video files. Use when user shares a video/GIF and wants to understand how to build it, clone a UI, reverse engineer a product, or extract tutorial steps. Triggers on "watch this video", "clone this", "reverse engineer", "how do I build this", "analyze this demo".

Images, Video & Audio

Linkly Quote Cards

logog782-cmyk/linkly-quote-cards

Linkly 金句卡 v2「双色印刷版」——把 Linkly 分类笔记里的金句印成双墨编辑印刷卡(halftone 网点影像+文字压图+活字落款)。当用户说出金句卡、金句卡 no.XX、金句海报、金句配图、印刷金句卡、双色金句卡、给这句话出张卡时使用本 skill。生图唯一走 ~/飞书/imagegen/gen.py(Seedream),逐字校验硬门。旧纸 zine 风为 v1 已归档版式,仅点名"zine 版/旧纸版"才复刻。

Images, Video & Audio

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.