skills.rest
wulaosiji
wulaosijiCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

whisper-stt

Transcribe local audio files to text using OpenAI Whisper models.

28|13|Updated Feb 27, 2026
Search Tags:#transcription#whisper#audio processing#local#privacy#speech to text
One-click install
npx skills add https://github.com/wulaosiji/skills --skill whisper-stt
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: whisper-stt
Source: https://github.com/wulaosiji/skills/tree/main/whisper-stt
Command: npx skills add https://github.com/wulaosiji/skills --skill whisper-stt

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides a free, private, and efficient way to convert spoken audio into written text directly on your local machine, eliminating the need for external APIs or data sharing.

Core Features & Use Cases

  • Local Transcription: Utilizes the OpenAI Whisper model for high-accuracy speech-to-text conversion without internet reliance.
  • Privacy-Focused: All processing happens locally, ensuring your audio data remains secure.
  • Multi-Language Support: Supports various languages, with specific emphasis on Chinese.
  • Model Selection: Offers a range of Whisper models (tiny to large) to balance speed, accuracy, and resource usage.
  • Use Case: Transcribe meeting recordings, dictate notes, or convert voice messages into text for easier searching and editing, all while maintaining data privacy.

Quick Start

Use the whisper-stt skill to transcribe the audio file named 'meeting_recording.mp3' using the base model and specifying Chinese language.

Frequently Asked Questions about whisper-stt

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 an external API?▼

Local speech-to-text transcription can be performed using the OpenAI Whisper model, ensuring all audio data remains secure and private on your machine without internet reliance.

What is the best way to convert spoken Chinese voice recordings into text offline?▼

Offline speech-to-text conversion for Chinese is supported by the Whisper model, allowing you to specify the target language during transcription to achieve high-accuracy text output.

Do I need PyTorch installed to run local speech-to-text transcription with Whisper?▼

You must install the openai-whisper package, and PyTorch is an optional dependency that provides accelerated processing capabilities for the speech-to-text transcription task.

How do I balance transcription speed and accuracy when processing audio files?▼

You can balance speed and accuracy by selecting from various Whisper models, ranging from tiny for faster processing to large for maximum transcription accuracy based on your resource constraints.

Can I use this local transcription approach for secure meeting recordings?▼

Yes, local speech-to-text processing is ideal for meeting recordings as it keeps sensitive audio data secure on your machine, converting voice messages into searchable text without data sharing.

Related Skills

Explore More Software Engineering Skills→
douglasjsdouglasjs

openai-whisper

Transcribe and translate local audio files using the OpenAI Whisper CLI.

Community
Intermediate
zinohomezinohome

markdown-converter

Convert PDFs, office files, images, audio, and web content into Markdown.

Community
Intermediate
steipetesteipete
385.7k

openai-whisper

Transcribe local audio files to text or subtitles using the Whisper CLI.

Community
Intermediate
martinholovskymartinholovsky
45

speech-to-text

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

Community
Advanced