whisper

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

Updated May 14, 2026

Search Tags:#translation #transcription #whisper #multilingual #speech-to-text #audio-processing

Ready to run

npx skills add https://github.com/SethyPagna/Secretary-Jarvis --skill whisper-sethypagna

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/SethyPagna/Secretary-Jarvis/tree/main/src/capabilities/optional-skills/mlops/whisper
Command: npx skills add https://github.com/SethyPagna/Secretary-Jarvis --skill whisper-sethypagna

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Whisper removes the manual burden of turning spoken audio into readable text, making it easier to capture meetings, interviews, podcasts, and video content across many languages.

Core Features & Use Cases

Speech-to-Text Transcription: Convert audio files into accurate transcripts for note-taking, documentation, and archive search.
Translation and Language Detection: Identify the spoken language and translate non-English audio into English when needed.
Multimedia Workflows: Generate subtitles, process batches of recordings, and handle noisy or multilingual audio for content teams and researchers.
Model Selection and Performance Tuning: Choose from multiple model sizes and use GPU acceleration for faster, higher-quality transcription.

Quick Start

Use the whisper skill to transcribe the attached audio file into text and translate it to English if you need a readable summary.

Frequently Asked Questions about whisper

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

FAQPage Schema

How do I transcribe audio files into text transcripts?▼

Audio transcription converts spoken recordings into readable text. You can transcribe podcasts, meetings, or interviews by applying speech-to-text processing to generate accurate, timestamped text output from your audio files.

Can I translate non-English audio into English text automatically?▼

Yes, speech-to-text translation can detect the spoken language in non-English audio and translate it directly into English text. This multilingual processing handles recordings across 99 languages to produce readable English summaries.

Does speech-to-text processing work with noisy or multilingual recordings?▼

Yes, speech-to-text processing handles noisy or multilingual audio recordings. It uses language detection and model selection to accurately process complex multimedia workflows and generate subtitles from challenging audio sources.

How do I speed up batch transcription for multiple audio files?▼

Batch transcription speed is improved by selecting smaller model sizes and enabling GPU acceleration. Tuning these performance parameters allows you to process multiple recordings faster while maintaining high-quality speech-to-text output.

Do I need ffmpeg to preprocess audio for speech-to-text conversion?▼

Yes, ffmpeg-based audio preprocessing is used to prepare recordings for speech-to-text conversion. It handles audio extraction and formatting before the transcription model processes the files to generate accurate text.

What is the best way to generate subtitles from video or audio content?▼

Generating subtitles involves running speech-to-text transcription on your multimedia content. By processing the audio track with language detection and timestamps, you create accurate text captions suitable for video workflows.