whisper

Transcribe audio in 99 languages and translate speech to English using OpenAI's Whisper model.

2|Updated Feb 4, 2026

Search Tags:#translation #speech recognition #transcription #audio processing #multilingual #ASR

Ready to run

npx skills add https://github.com/zhuangbiaowei/smart_bot --skill whisper-zhuangbiaowei

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/zhuangbiaowei/smart_bot/tree/main/skills/whisper
Command: npx skills add https://github.com/zhuangbiaowei/smart_bot --skill whisper-zhuangbiaowei

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the process of converting audio into text, enabling efficient transcription, translation, and analysis of spoken content.

Core Features & Use Cases

Multilingual Transcription: Transcribe audio in 99 languages.
Translation: Translate spoken audio directly into English text.
Use Case: Transcribe a multilingual podcast episode, automatically generating accurate text for each speaker and translating non-English segments into English.

Quick Start

Use the whisper skill to transcribe the attached audio file 'meeting.mp3'.

Frequently Asked Questions about whisper

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

FAQPage Schema

How do I transcribe a multilingual podcast episode into text?▼

To transcribe a multilingual podcast, this Skill uses OpenAI's Whisper model to convert spoken audio into accurate text, supporting transcription across 99 different languages.

Can I translate spoken audio directly into English text?▼

Yes, you can translate spoken audio directly into English text. The Skill leverages the Whisper model to process non-English segments and automatically generate English translations.

Does audio transcription work with the mp3 file format?▼

Audio transcription works with mp3 files and other formats. The Skill uses ffmpeg for audio processing, ensuring robust speech recognition and translation across various input types.

Do I need ffmpeg installed for speech recognition processing?▼

Yes, ffmpeg is required for audio processing. Along with openai-whisper, transformers, and torch, it handles the underlying audio decoding necessary for multilingual transcription.

What is the best way to handle speech recognition for multiple languages?▼

The best way to handle multilingual speech recognition is using Whisper. It offers various model sizes to balance speed and accuracy when transcribing audio in 99 languages.

Why does transcription speed vary during audio-to-text conversion?▼

Transcription speed varies based on the Whisper model size chosen. The Skill supports multiple model sizes, allowing users to select the optimal balance of processing speed and accuracy.