whisper

Name: whisper
Availability: InStock
Author: daddyelonmusk69

Convert multilingual audio recordings into text transcripts and English translations.

Updated Apr 12, 2026

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

Ready to run

npx skills add https://github.com/DaddyElonMusk69/motis-agent --skill whisper-daddyelonmusk69

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/DaddyElonMusk69/motis-agent/tree/main/skills/mlops/models/whisper
Command: npx skills add https://github.com/DaddyElonMusk69/motis-agent --skill whisper-daddyelonmusk69

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Convert audio recordings into accurate, timestamped text and English translations so teams can index, search, and analyze speech without manual transcription.

Core Features & Use Cases

Multilingual ASR: Transcribe 99 languages with model-size options for speed or accuracy tradeoffs.
Translation & Detection: Translate non-English audio to English and identify spoken language automatically.
Use Case: Batch-transcribe podcast episodes or meeting recordings, produce SRT/VTT subtitles, and extract segment timestamps for downstream analysis.

Quick Start

Transcribe audio.mp3 with the turbo model to produce an English transcript with timestamps and save it as transcript.txt.

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 recordings into timestamped text?▼

Transcribe multilingual audio recordings into timestamped text by processing files with speech-to-text models that support 99 languages. The system automatically identifies the spoken language and outputs segment-level timestamps for accurate text transcripts.

Can I automatically translate non-English audio to English during transcription?▼

Yes, you can automatically translate non-English audio to English during transcription. The process detects the spoken language and generates an English translation alongside the original timestamped segments for easy analysis.

How do I generate SRT subtitles from podcast or meeting recordings?▼

Generate SRT subtitles from podcast or meeting recordings by running batch audio processing with timestamped segment extraction. This converts the spoken audio into accurate text files formatted for subtitle use.

Does faster-whisper support GPU acceleration for batch audio processing?▼

Yes, faster-whisper supports GPU acceleration for batch audio processing. This integration enables streaming capabilities and allows you to trade transcription speed for accuracy using multiple model sizes.

What's the best way to balance speed and accuracy for speech-to-text conversion?▼

Balance speed and accuracy for speech-to-text conversion by selecting from multiple model sizes available in the system. You can also use initial prompt context to guide the transcription and improve output accuracy.

Do I need ffmpeg to process audio files for transcription?▼

Yes, ffmpeg is integrated into the workflow to process audio files for transcription. It handles the audio decoding required before converting the recordings into accurate text transcripts and English translations.