skills.rest
MedTiLab
MedTiLabCOMMUNITY
Explore all skills by this author →
GitHub

whisper

Transcribe and translate multilingual audio into text using OpenAI Whisper models.

5|2|Updated Aug 10, 2026
Search Tags:#Whisper#translation#speech recognition#subtitles#transcription#audio processing#ASR
One-click install
npx skills add https://github.com/MedTiLab/Auto-meta-analysis --skill whisper-medtilab
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/MedTiLab/Auto-meta-analysis/tree/main/skills/multimodal/whisper
Command: npx skills add https://github.com/MedTiLab/Auto-meta-analysis --skill whisper-medtilab

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Converting speech from audio and video files into accurate text is time-consuming when done manually, especially across multiple languages. This Skill automates speech-to-text transcription, translation to English, and language identification using OpenAI's Whisper model. ## Core Features & Use Cases - Multilingual Transcription: Transcribe audio in 99 languages with six model sizes (tiny to large/turbo) to balance speed and accuracy. - Translation & Language Detection: Translate any supported language's audio into English and automatically detect the spoken language. - Flexible Output Formats: Generate plain text, SRT/VTT subtitles, or JSON with word-level timestamps via Python API or command line. - Use Case: Imagine you recorded a one-hour podcast interview in Spanish. Use this Skill to transcribe it with timestamps, generate English subtitles in SRT format, and produce a translated transcript for show notes. ## Quick Start Transcribe the attached audio file 'interview.mp3' into text with timestamps using the turbo model.

Frequently Asked Questions about whisper

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

FAQPage Schema
How do I transcribe audio to text with Whisper in Python?▼

Install openai-whisper and ffmpeg, then load a model with whisper.load_model("base") and call model.transcribe("audio.mp3"). The result contains the full text plus timestamped segments you can iterate over.

Which Whisper model size should I use for transcription?▼

Use turbo for the best speed-to-quality balance and base for quick prototyping. The large model (1550M parameters) gives highest accuracy but needs about 10 GB VRAM, while tiny runs fastest with lower accuracy.

Can Whisper translate audio in other languages to English?▼

Yes, Whisper supports translation to English from any of its 99 supported languages. Pass task="translate" to the transcribe call, and the output text will be in English regardless of the source language.

Does Whisper support GPU acceleration for faster transcription?▼

Yes, Whisper automatically uses a CUDA GPU when available, giving 10-20x speedup over CPU. You can force a device with whisper.load_model("turbo", device="cuda") or device="cpu".

What are the limitations of Whisper speech recognition?▼

Whisper can hallucinate or repeat text, accuracy degrades on audio longer than 30 minutes, and it provides no speaker diarization. It is also not suitable for real-time live captioning due to latency.

Related Skills

Explore More Content & Communication Skills→
buda-aibuda-ai
25

audio-extractor

Extract and enhance audio from video files for MP3/WAV/AAC output.

Official
Intermediate
one-ieone-ie
129

youtube-subs

Extract YouTube subtitles into clean text transcripts for LLM processing.

Official
Intermediate
h4vzzh4vzz
33

meeting-transcription

Transcribe meeting audio with speaker diarization and timestamped summaries.

Community
Advanced
framerslabframerslab

streaming-stt-deepgram

Transcribe live speech via Deepgram's WebSocket API with speaker diarization.

Official
Advanced