whisper

whisper is a skill for Claude Code, Codex from graniet/kheish. It costs 64 tokens per session (2,184 once invoked), scanned B, a copy of whisper, Apache-2.0.

Guidance for Whisper, OpenAI's speech-recognition model, which turns spoken audio into text and can translate speech into English. It also covers identifying the spoken language and processing multilingual audio.

In plain words
What is it for?
Use it for podcast, video, meeting, or other audio transcription, multilingual speech processing, and translation to English.
Why use it?
It helps choose and use Whisper for audio transcription without building speech recognition from scratch. The guidance covers different model sizes and common speech-processing tasks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for podcast, video, meeting, or other audio transcription, multilingual speech processing, and translation to English.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/graniet/kheish/whisper
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add graniet/kheish --skill whisper
Clone the repo
git clone --depth 1 https://github.com/graniet/kheish

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for whisper

README.md
[![agentmods](https://agentmods.dev/badge/skills/graniet/kheish/whisper/github.svg)](https://agentmods.dev/skills/graniet/kheish/whisper)
Your own site
<a href="https://agentmods.dev/skills/graniet/kheish/whisper"><img src="https://agentmods.dev/badge/skills/graniet/kheish/whisper/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for whisper

Your own site · 80×15
<a href="https://agentmods.dev/skills/graniet/kheish/whisper"><img src="https://agentmods.dev/badge/skills/graniet/kheish/whisper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,184 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 89% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00064 $0.02184
Opus 5 $0.00032 $0.01092
Sonnet 5 $0.00013 $0.00437
Haiku 4.5 $0.00006 $0.00218

Measured 9d ago against content hash e81a517aa06f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

whisper scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

# Ubuntu: sudo apt install ffmpeg
Origin

This is a copy

89% identical to whisper — 42 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/mlops/models/whisper/SKILL.md · 346 lines

How it starts

The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kheish Compatibility

This skill is repo-local and stays inactive until explicitly activated.

When the original instructions refer to legacy tool names, use these Kheish mappings:

  • terminal => bash
  • web_extract => web_fetch, plus web_search when discovery is needed
  • search_files => grep_search and glob_search
  • browser_* tools require a browser-capable surfaced tool or MCP; if none is available, use the closest available surface and say so explicitly

When the instructions mention local helper files, resolve them from ${KHEISH_SKILL_DIR}.

Whisper - Robust Speech Recognition

OpenAI's multilingual speech recognition model.

When to use Whisper

Use when:

  • Speech-to-text transcription (99 languages)
  • Podcast/video transcription
  • Meeting notes automation
  • Translation to English
  • Noisy audio transcription
  • Multilingual audio processing

Metrics:

  • 72,900+ GitHub stars
  • 99 languages supported
  • Trained on 680,000 hours of audio
  • MIT License

Use alternatives instead:

  • AssemblyAI: Managed API, speaker diarization
  • Deepgram: Real-time streaming ASR
  • Google Speech-to-Text: Cloud-based

Quick start

Installation

# Requires Python 3.8-3.11
pip install -U openai-whisper

# Requires ffmpeg
# macOS: brew install ffmpeg
# Ubuntu: sudo apt install ffmpeg
# Windows: choco install ffmpeg

Basic transcription

import whisper

# Load model
model = whisper.load_model("base")

# Transcribe
result = model.transcribe("audio.mp3")

# Print text
print(result["text"])

# Access segments
for segment in result["segments"]:
    print(f"[{segment['start']:.2f}s - {segment['end']:.2f}s] {segment['text']}")

Model sizes

# Available models
models = ["tiny", "base", "small", "medium", "large", "turbo"]

# Load specific model
model = whisper.load_model("turbo")  # Fastest, good quality
Model Parameters English-only Multilingual Speed VRAM
tiny 39M ~32x ~1 GB
base 74M ~16x ~1 GB
small 244M ~6x ~2 GB
medium 769M ~2x ~5 GB
large 1550M 1x ~10 GB
turbo 809M ~8x ~6 GB

Read the full file on GitHub · 346 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 346 lines · 64 tokens per session scan B e81a517aa06f

Subscribe to this mod's changes

whisper is a skill published in the GitHub repository graniet/kheish (227 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 64 tokens to every session and 2,184 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). It is 89% identical to whisper, differing in 42 lines, and is treated as a copy.

Related

Other skills, from other repositories

llm-evaluation

LLM evaluation and testing patterns including prompt testing, hallucination detection, benchmark creation, and quality metrics. Use when testing LLM applications, validating prompt quality, implementing systematic evaluation, or measuring LLM performance.

stefan-jansen/claude-code-toolkit · 47 tokens

huggingface-transformers

Hugging Face Transformers best practices including model loading, tokenization, fine-tuning workflows, and inference optimization. Use when working with transformer models, fine-tuning LLMs, implementing NLP tasks, or optimizing transformer inference.

stefan-jansen/claude-code-toolkit · 52 tokens

rag-implementation

Comprehensive guide to implementing RAG systems including vector database selection, chunking strategies, embedding models, and retrieval optimization. Use when building RAG systems, implementing semantic search, optimizing retrieval quality, or debugging RAG performance issues.

stefan-jansen/claude-code-toolkit · 50 tokens

persona-model-trainer

Fine-tune any HuggingFace instruction-tuned model (Gemma 4, Qwen 3, Llama, Phi, Mistral, and more) on persona data from anyone-skill. Produces a self-contained, locally runnable persona model — no cloud API required.

acnlabs/OpenPersona · 63 tokens

constitutional-ai

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.

synthetic-sciences/openscience · 58 tokens

agent-builder

Build production-ready LLM agents with LangGraph, tool use, memory, streaming, and error handling. Use when designing or implementing an AI agent, multi-agent system, or agentic workflow.

chandrudp29/skillhub · 42 tokens