whisper-stt

Name: whisper-stt
Availability: InStock
Author: okbest2024

Transcribe local audio files into text using OpenAI Whisper.

Updated Mar 18, 2026

Search Tags:#offline #transcription #whisper #audio-to-text #subtitle-generation #local-stt

Ready to run

npx skills add https://github.com/okbest2024/openclaw-backup --skill whisper-stt-okbest2024

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: whisper-stt
Source: https://github.com/okbest2024/openclaw-backup/tree/main/workspace/skills/whisper-stt
Command: npx skills add https://github.com/okbest2024/openclaw-backup --skill whisper-stt-okbest2024

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill enables fully offline speech-to-text transcription using OpenAI Whisper, eliminating cloud API costs and privacy concerns for local audio/video transcription needs.

Core Features & Use Cases

Local transcription: transcribes audio files on-device without sending data to external servers.
Multi-format support: handles mp3, wav, m4a, ogg and more, with optional language hints for better accuracy.
Subtitle generation: exports json/txt/srt/vtt outputs suitable for captions and transcripts.

Quick Start

Transcribe a local audio file using the transcribe.py script and choose your preferred model and output format.

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 cloud API costs?▼

Local audio transcription without cloud API costs is achieved by running the OpenAI Whisper model entirely on your device. This skill processes audio files offline, ensuring data privacy while converting speech to text.

What audio and subtitle formats are supported for offline speech-to-text?▼

Offline speech-to-text supports common audio formats including mp3, wav, m4a, and ogg. It exports transcribed text into json, txt, srt, and vtt formats, making it suitable for generating video subtitles and plain text transcripts.

Do I need openai-whisper and torch installed to transcribe audio on my machine?▼

Yes, you need openai-whisper and torch installed to perform local audio transcription. These dependencies provide the underlying machine learning framework and model required to process audio files entirely on your device.

What is the best way to generate SRT subtitles from a video transcript locally?▼

The best way to generate SRT subtitles locally is using a Whisper-based transcription tool that operates offline. By processing the audio file with openai-whisper, you can directly export SRT formatted subtitle files without relying on external servers.

Can I improve transcription accuracy by providing language hints for mp3 or m4a files?▼

Yes, providing language hints improves transcription accuracy for audio files like mp3 and m4a. Specifying the spoken language helps the local Whisper model narrow its recognition scope, resulting in more precise text conversion.

Are there limitations to processing large audio files completely offline with Whisper?▼

Processing large audio files completely offline with Whisper is limited by your local hardware capabilities, specifically GPU memory and compute power. Transcription speed and file size capacity depend entirely on the torch configuration and your device resources.