skills.rest
vivekgoquest
vivekgoquestCOMMUNITY
Explore all skills by this author →
GitHub

whisper

Transcribe and translate speech audio in 99 languages using OpenAI Whisper.

Updated Aug 22, 2026
Search Tags:#Whisper#translation#transcription#audio processing#multilingual#speech-to-text#ASR
One-click install
npx skills add https://github.com/vivekgoquest/hermes-agent-stable --skill whisper-vivekgoquest
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: whisper
Source: https://github.com/vivekgoquest/hermes-agent-stable/tree/main/optional-skills/mlops/whisper
Command: npx skills add https://github.com/vivekgoquest/hermes-agent-stable --skill whisper-vivekgoquest

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Converting spoken audio into text manually is slow and error-prone, especially across multiple languages, noisy recordings, or long podcast and meeting files. ## Core Features & Use Cases - Multilingual Transcription: Transcribe speech in 99 languages with automatic language detection and word-level timestamps. - Translation to English: Convert audio in any supported language directly into English text using the translate task. - Flexible Model Sizes: Choose from tiny to large/turbo models to balance speed, accuracy, and VRAM usage, with GPU acceleration. - Use Case: Transcribe a folder of recorded podcast episodes into SRT subtitle files by running the whisper CLI with the turbo model and srt output format. ## Quick Start Ask the agent to transcribe the attached audio file 'meeting.mp3' into text with timestamps using the Whisper 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?▼

Load a model with whisper.load_model("base") and call model.transcribe("audio.mp3"). The result dictionary 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 and quality balance, or base for quick prototyping. Larger models like large improve accuracy for low-resource languages but need up to 10 GB of VRAM.

Can Whisper translate foreign language audio to English?▼

Yes, pass task="translate" to model.transcribe and Whisper converts speech in any supported language into English text. Translation output is always English regardless of the source language.

Does Whisper support real-time streaming transcription?▼

OpenAI Whisper is not designed for live captioning due to latency. For streaming audio, use faster-whisper, which runs about 4x faster and supports segment-by-segment output.

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. Background noise and strong accents also reduce transcription quality.

Related Skills

Explore More Software Engineering Skills→
lordmaculordmacu
6

Video Frames

Extract frames and audio tracks from video files using ffmpeg.

Community
Intermediate
kreuzberg-devkreuzberg-dev
9.2k

chunking

Split extracted text into sized chunks for LLM context windows and RAG ingestion.

Official
Intermediate
bl1nk-botbl1nk-bot
3

transcribe

Transcribe audio files into text transcripts with optional speaker diarization.

Official
Intermediate
framerslabframerslab

streaming-stt-deepgram

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

Official
Advanced