skills.rest
aryankumar06
aryankumar06COMMUNITY
Explore all skills by this author →
Website𝕏@aryankumar_5GitHub

audio-transcription

Transcribe audio files into text and SRT subtitles using Whisper.

16|2|Updated Mar 16, 2026
Search Tags:#cli#offline#transcription#whisper#audio#ffmpeg#srt
One-click install
npx skills add https://github.com/aryankumar06/claude-code-skills --skill audio-transcription-aryankumar06
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: audio-transcription
Source: https://github.com/aryankumar06/claude-code-skills/tree/main/audio-transcription-skill
Command: npx skills add https://github.com/aryankumar06/claude-code-skills --skill audio-transcription-aryankumar06

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai-whisper, ffmpeg, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Transcribing long audio conversations is time-consuming and error-prone; this skill provides automatic offline transcription and subtitle generation using Whisper.

Core Features & Use Cases

  • Offline transcription: Transcribes audio locally after model download for privacy and reliability.
  • Flexible outputs: Produces plain text transcripts or SRT subtitles from a single run.
  • Widely applicable: Ideal for lectures, meetings, podcasts, and voice memos needing quick accessibility.
  • Language support: Auto-detects language with option to override.
  • CLI-driven workflow: Simple command-line usage to integrate into automation pipelines.

Quick Start

Transcribe an audio file by running the transcription script with the path to your audio file.

Frequently Asked Questions about audio-transcription

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe audio to text offline using Whisper?▼

You can generate SRT subtitles offline by running the provided CLI script with your audio file, which uses openai-whisper to automatically detect speech and output timestamped subtitle files alongside plain text.

What do I need to run local audio transcription for podcasts?▼

Local audio transcription requires Python 3.8+, the openai-whisper library, and FFmpeg installed on your system to decode and process audio files into text or SRT outputs.

Can I auto-detect language when transcribing voice memos?▼

Yes, the transcription script auto-detects the spoken language in your voice memos by default, with an option to manually override the language setting for accurate offline text generation.

How do I generate SRT subtitles from an audio file?▼

You can generate SRT subtitles offline by running the provided CLI script with your audio file, which uses openai-whisper to automatically detect speech and output timestamped subtitle files alongside plain text.

Why use offline transcription instead of cloud speech-to-text?▼

Offline transcription ensures privacy and reliability by processing audio locally on your machine, making it suitable for sensitive meetings or lectures where uploading audio to cloud speech-to-text services is not permitted.

Related Skills

Explore More Content & Communication Skills→
icyzhicyzh
1

whisper

Transcribe and translate audio files into text using OpenAI Whisper.

Community
Intermediate
koukokouko

youtube-get-transcript

Download YouTube subtitles and transcripts as SRT and TXT files using yt-dlp.

Community
Intermediate
luan-thnhluan-thnh

media-processing

Orchestrate FFmpeg, ImageMagick, and RMBG to automate media processing tasks.

Community
Advanced
martinholovskymartinholovsky
45

speech-to-text

Transcribe audio files locally with Faster Whisper speech-to-text.

Community
Advanced