skills.rest
CoachSteff
CoachSteffCOMMUNITY
Explore all skills by this author →
Website𝕏@coachsteffGitHub

transcriber-local

Run Whisper models locally to transcribe audio and video files offline.

1|Updated Dec 7, 2025
Search Tags:#offline#transcription#whisper#audio#privacy#timestamps#local-model
One-click install
npx skills add https://github.com/CoachSteff/superskills --skill transcriber-local
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: transcriber-local
Source: https://github.com/CoachSteff/superskills/tree/main/superskills/transcriber-local
Command: npx skills add https://github.com/CoachSteff/superskills --skill transcriber-local

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Privacy-focused offline transcription by running Whisper models locally to avoid cloud processing and data exposure.

Core Features & Use Cases

  • On-device transcription with local Whisper models (tiny to large)
  • Word-level timestamps and multiple output formats (TXT, JSON, SRT, VTT)
  • Batch processing and GPU acceleration for improved performance
  • Suitable for sensitive content, compliance workflows, and offline workloads

Quick Start

Invoke LocalTranscriber with your preferred model_size and transcribe a file locally.

Frequently Asked Questions about transcriber-local

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

FAQPage Schema
How do I transcribe audio files locally without sending data to the cloud?▼

Offline transcription runs Whisper models directly on your device to convert audio files to text without cloud processing, ensuring sensitive content remains completely private and compliant with data protection regulations.

What output formats and timestamp options are available for offline transcription?▼

Offline transcription supports TXT, JSON, SRT, and VTT output formats, with optional word-level timestamps for precise alignment, enabling seamless integration into subtitles, documentation, and compliance workflows.

Do I need to install openai-whisper to perform local audio transcription?▼

Yes, local transcription requires the openai-whisper installation and local model caches, handling model selection from tiny to large sizes, batching, and format export automatically for on-device workloads.

Can I batch process multiple audio and video files locally with Whisper?▼

Batch processing and GPU acceleration support transcribing multiple audio and video files locally, improving performance for large offline workloads while maintaining privacy and avoiding cloud data exposure.

Is local Whisper transcription suitable for compliance-driven workflows?▼

Yes, privacy-preserving offline transcription is designed for compliance-driven workflows and sensitive content, running entirely on-device to avoid data exposure during audio and video file processing.

What's the best way to transcribe sensitive audio without internet access?▼

Running Whisper models locally provides the best way to transcribe sensitive audio offline, avoiding cloud processing entirely while offering model selection, batch processing, and multiple output formats for on-device workloads.

Related Skills

Explore More Content & Communication Skills→
VYRE-StudiosVYRE-Studios

whisper

Transcribe speech from audio files into text using OpenAI Whisper models.

Official
Intermediate
maxgent-aimaxgent-ai

audio-transcribe

Transcribe audio and video files with word-level timestamps using WhisperX.

Official
Advanced
SethyPagnaSethyPagna

whisper

Transcribe spoken audio into text with Whisper model selection and timestamps.

Community
Intermediate
wulaosijiwulaosiji
28

whisper-stt

Transcribe local audio files to text using OpenAI Whisper models.

Community
Intermediate