whisper

Transcribe multilingual audio into text with timestamps and translation options.

Updated Mar 16, 2026

Search Tags:#transcription #whisper #nlp #audio #multilingual #speech-to-text #languages

Ready to run

npx skills add https://github.com/arsity/scholar-tools --skill whisper-arsity

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/arsity/scholar-tools/tree/main/vendor/ai-research-skills/18-multimodal/whisper
Command: npx skills add https://github.com/arsity/scholar-tools --skill whisper-arsity

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Whisper solves the challenge of turning spoken language from audio and video into accurate, searchable transcripts across many languages, enabling faster transcription, translation, and analysis.

Core Features & Use Cases

Multilingual transcription: supports 99 languages with automatic language detection.
Translation to English: translate non-English transcripts for quick understanding.
Model variety: selectable sizes (tiny to large) to balance speed and accuracy in diverse environments.
Use Case: transcribe interviews, podcasts, meetings, or archival recordings into readable text for search and analysis.

Quick Start

Install the whisper package, load a model (e.g., base or turbo), and call transcribe on your audio file to obtain text.

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 files into searchable text?▼

Multilingual speech-to-text transcription converts spoken audio into accurate text across 99 languages. You can automatically detect the language in your recordings or specify it manually to generate readable transcripts for podcasts, interviews, and meetings.

Can I translate non-English audio transcripts into English?▼

Yes, translation to English is supported for non-English audio transcripts. The speech-to-text pipeline can automatically transcribe multilingual recordings and translate the output into English for quick understanding and analysis.

How do I balance transcription speed and accuracy for large audio archives?▼

You can balance transcription speed and accuracy by selecting from various model sizes, ranging from tiny to large. Loading a smaller model speeds up processing for large archival recordings, while larger models deliver higher accuracy.

Does speech-to-text transcription support adding timestamps for meetings?▼

Yes, timestamp generation is supported for transcription workflows. Adding timestamps to meeting and interview transcripts helps segment spoken dialogue and aligns the text output with specific points in the original audio recording.

What is the best way to transcribe podcasts across multiple languages?▼

The best way to transcribe podcasts across multiple languages is using automatic language detection within a multilingual speech-to-text model. This approach accurately processes diverse audio inputs and outputs readable text for search and analysis.

Do I need to specify a language for automatic speech-to-text detection?▼

No, you do not need to specify a language for automatic speech-to-text detection. The transcription model automatically identifies the spoken language from the audio input, though you can manually specify it to fit specific pipeline requirements.