skills.rest
Tommy-yw
Tommy-ywCOMMUNITY
Explore all skills by this author →
GitHub

whisper

Transcribe spoken audio to text in 99 languages using OpenAI's Whisper model.

539|39|Updated May 1, 2026
Search Tags:#speech recognition#audio processing#multilingual#text conversion#ASR
One-click install
npx skills add https://github.com/Tommy-yw/RunbookHermes --skill whisper-tommy-yw
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/Tommy-yw/RunbookHermes/tree/main/optional-skills/mlops/whisper
Command: npx skills add https://github.com/Tommy-yw/RunbookHermes --skill whisper-tommy-yw

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill allows users to quickly convert spoken language to written text, eliminating the need for manual transcription.

Core Features & Use Cases

  • Speech Recognition: Supports transcription of speech to text in 99 languages.
  • Audio Transcription: Convert spoken words to text with accurate transcription and translation capabilities.
  • Use Case: Record a meeting and quickly transcribe the conversation to text, enabling easier search and sharing of the discussion.

Quick Start

Load the Whisper model with 'whisper.load_model("base")' and use 'model.transcribe("audio.mp3")' to convert an audio file to text.

Frequently Asked Questions about whisper

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

FAQPage Schema
How do I convert spoken audio to text for meeting transcription?▼

To convert spoken audio to text, load the Whisper model using 'whisper.load_model("base")' and call 'model.transcribe("audio.mp3")' on your audio file to instantly generate a written transcript of the conversation.

Does speech recognition support multilingual audio processing?▼

Yes, multilingual speech recognition is fully supported. The transcription service leverages OpenAI's Whisper model to accurately process and convert spoken language to written text across 99 different languages.

Can I use Whisper with torch and transformers for text conversion?▼

Yes, Whisper operates using torch and transformers dependencies. You can execute accurate speech to text conversion and translation capabilities directly within this Python environment.

What is the best way to transcribe audio files for content analysis?▼

The best way to transcribe audio for content analysis is using the Whisper model. It eliminates manual transcription by converting spoken words into searchable text, enabling efficient audio-visual documentation and analysis.

Are there limitations when converting spoken language to written text?▼

While Whisper supports 99 languages for transcription, limitations depend on audio clarity and the loaded model size. Using the base model provides quick results, but complex audio-visual documentation may require advanced configuration.

Related Skills

Explore More Data & Analytics Skills→
zeronx798zeronx798

whisper

Transcribe multilingual audio files into text using OpenAI's Whisper model.

Community
Intermediate
beshkenadzebeshkenadze
3

meeting-notes

Convert meeting transcripts into structured notes with decisions and action items.

Community
Basic
kngender5kngender5

colab-audio-inference

Serve ASR, TTS, and music generation models via Gradio on Google Colab GPU.

Community
Advanced
guoqiaoguoqiao

mlx-stt

Transcribe audio files locally using MLX on Apple Silicon.

Community
Intermediate