openai-whisper

A local speech-to-text tool that uses the Whisper command-line program to turn audio into text. It can also translate speech and create subtitle files.

In plain words
What is it for?
Use it to transcribe MP3 or M4A recordings, translate spoken audio, or produce SRT subtitles.
Why use it?
It transcribes audio on the local computer without requiring an API key.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/the-open-agent/openagent/openai-whisper
Any agent
npx skills add the-open-agent/openagent --skill openai-whisper
Clone the repo
git clone --depth 1 https://github.com/the-open-agent/openagent

Made for: Claude Code, Codex.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 233 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00018 $0.00233
Opus 5 $0.00009 $0.00117
Sonnet 5 $0.00004 $0.00047
Haiku 4.5 $0.00002 $0.00023

Measured yesterday against content hash 7e8d2749dee0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

openai-whisper scanned grade A with 0 findings 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 yesterday.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

8 near-identical copies found in the catalogue:

skills/openai-whisper/SKILL.md · 39 lines

What it actually says

Whisper (CLI)

Use whisper to transcribe audio locally.

Quick start

  • whisper /path/audio.mp3 --model medium --output_format txt --output_dir .
  • whisper /path/audio.m4a --task translate --output_format srt

Notes

  • Models download to ~/.cache/whisper on first run.
  • --model defaults to turbo on this install.
  • Use smaller models for speed, larger for accuracy.
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. yesterday First seen · 39 lines · 18 tokens per session scan A 7e8d2749dee0

Subscribe to this mod's changes

openai-whisper is a skill published in the GitHub repository the-open-agent/openagent (5,592 stars, last pushed 11d ago), licensed Apache-2.0. It adds 18 tokens to every session and 233 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

Stable Diffusion

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

agentic-in/elephant-agent · 47 tokens

Whisper

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…

agentic-in/elephant-agent · 67 tokens

nano-banana-pro

Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro). Use when the user asks to create an image, generate a picture, produce AI-generated artwork, edit a photo, compose multiple images, or upscale an image to higher resolution. Supports text-to-image generation, single-image editing, and multi-image…

elizaOS/eliza · 74 tokens

spotify-player

Terminal Spotify playback/search via spogo (preferred) or spotifyplayer. Use when the user asks to play music, search for a song, skip a track, pause playback, check what is currently playing, control Spotify, list audio devices, or manage a Spotify queue from the terminal.

elizaOS/eliza · 60 tokens

blucli

BluOS CLI (blu) for discovery, playback, grouping, and volume control of Bluesound and NAD speakers. Use when the user wants to play music, stream audio, control speakers, adjust volume, group or ungroup Bluesound players, search TuneIn radio, or manage multi-room streaming setups.

elizaOS/eliza · 64 tokens

fashion-campaign-production

Provider-independent production workflow for AI-assisted fashion campaigns, lookbooks, editorial fashion films, ecommerce/editorial hybrids, social cutdowns, virtual try-on assets, generated model/lifestyle ads, and retouched fashion visuals; use when an agent must plan, prompt, produce, review, localize, or deliver…

calesthio/generative-media-skills · 95 tokens