skills.rest
jleechanorg
jleechanorgOFFICIAL
Explore all skills by this author →
GitHub

whisper

Transcribe multilingual audio into text using Python and CLI.

Updated Jun 28, 2026
Search Tags:#translation#transcription#whisper#multilingual#audio-processing#speech-recognition
One-click install
npx skills add https://github.com/jleechanorg/hermes-agent --skill whisper-jleechanorg
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/jleechanorg/hermes-agent/tree/main/optional-skills/mlops/whisper
Command: npx skills add https://github.com/jleechanorg/hermes-agent --skill whisper-jleechanorg

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Whisper provides robust, multilingual speech recognition to transcribe audio into accurate text across 99 languages, enabling transcripts, captions, and translations.

Core Features & Use Cases

  • Multilingual transcription: Transcribe audio to text in many languages.
  • Translation: Translate transcripts to English.
  • Batch and real-time use with Python APIs and CLI.

Quick Start

Transcribe an audio file by loading the desired Whisper model and invoking the transcribe method.

Frequently Asked Questions about whisper

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

FAQPage Schema
How do I transcribe multilingual audio into text for meeting minutes and podcasts?▼

Whisper transcribes multilingual audio into text using Python scripts or CLI, supporting 99 languages for podcast transcription, meeting minutes, and media archiving workflows.

Can I translate audio transcripts to English using speech recognition?▼

Whisper provides speech recognition that translates transcripts to English. It processes audio across 99 languages and outputs text suitable for multilingual content localization and translation workflows.

Do I need ffmpeg and a specific Python version for audio transcription?▼

Audio transcription requires Python 3.8-3.11 and ffmpeg for many pipelines. You select a model size from tiny to large depending on your accuracy and performance needs for processing audio files.

What is the best way to add captions and subtitles across multiple languages?▼

Whisper generates multilingual transcriptions suitable for captions by processing audio through Python APIs or CLI. It outputs text across 99 languages for media archiving and content localization.

Does speech recognition work for both batch processing and real-time transcription?▼

Whisper supports batch and real-time audio transcription with Python APIs and CLI. You process recorded files for archiving or transcribe live audio for immediate multilingual text generation.

Why does audio transcription fail or have limitations with certain formats?▼

Audio transcription requires ffmpeg for many pipelines, so missing dependencies cause failures. Limitations include Python 3.8-3.11 constraints and model size trade-offs affecting accuracy across 99 languages.

Related Skills

Explore More Software Engineering Skills→
thisismynewfmail-uithisismynewfmail-ui

whisper

Transcribe and translate audio across 99 languages using Whisper ASR models.

Community
Intermediate
MaosixianMaosixian

openclaw-youtube-transcript

Convert YouTube video subtitles and captions to text transcripts using yt-dlp.

Community
Intermediate
armoin2018armoin2018
4

ailey-tools-audio

Automate audio format conversion, extraction, and transcription with FFmpeg and Whisper.

Community
Advanced
ericfitzericfitz
2

translate_to_language

Translate English text to a target language while preserving placeholders and formatting.

Community
Intermediate