whisper

whisper is a skill for Claude Code, Codex from trpc-group/trpc-agent-go. It costs 13 tokens per session (552 once invoked), scanned B, original, Apache-2.0.

A tool for turning audio files into written text with OpenAI Whisper, a speech-recognition system. It supports common audio formats, multiple languages, optional timestamps, and text or JSON output.

In plain words
What is it for?
Transcribing MP3, WAV, M4A, FLAC, and OGG files, detecting or selecting a language, choosing a model size, adding word timestamps, and saving plain-text or JSON results.
Why use it?
It removes the need to transcribe recordings manually and can preserve timing information when the transcript needs to match the audio.

Skill for Claude CodeCodex

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

Good fit Transcribing MP3, WAV, M4A, FLAC, and OGG files, detecting or selecting a language, choosing a model size, adding word timestamps, and saving plain-text or JSON results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/trpc-group/trpc-agent-go/whisper
About the project

tRPC-Agent-Go is a Go framework for building AI agent applications with language models, graph-based workflows, tools, memory, retrieval, evaluation, and observability. Go developers use it to create deployable agent systems that can integrate with A2A, AG-UI, and MCP. The catalogue add-ons provide reusable workflows and agent integrations for the framework.

trpc-group/trpc-agent-go · 1,770 stars · on GitHub · trpc-group.github.io

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 trpc-group/trpc-agent-go --skill whisper
Clone the repo
git clone --depth 1 https://github.com/trpc-group/trpc-agent-go

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/trpc-group/trpc-agent-go/whisper/github.svg)](https://agentmods.dev/skills/trpc-group/trpc-agent-go/whisper)
Your own site
<a href="https://agentmods.dev/skills/trpc-group/trpc-agent-go/whisper"><img src="https://agentmods.dev/badge/skills/trpc-group/trpc-agent-go/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/trpc-group/trpc-agent-go/whisper"><img src="https://agentmods.dev/badge/skills/trpc-group/trpc-agent-go/whisper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 552 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Privilege Escalation · line 75
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
How audits are shown
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 5.1 $0.00013 $0.00552
Opus 5 $0.00006 $0.00276
Sonnet 5 $0.00003 $0.00110
Haiku 4.5 $0.00001 $0.00055

Measured 9d ago against content hash 8c6d3ac6deb9, 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/transcribe.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

sudo apt-get install ffmpeg # Ubuntu/Debian
examples/skill/skills/whisper/SKILL.md · 77 lines

What it actually says

Whisper Audio Transcription Skill

Transcribe audio files to text using OpenAI Whisper.

Capabilities

  • Transcribe audio files (MP3, WAV, M4A, FLAC, OGG, etc.) to text
  • Support for 90+ languages with auto-detection
  • Optional timestamp generation
  • Multiple model sizes (tiny/base/small/medium/large)
  • Output in plain text or JSON format

Usage

Basic Transcription

python3 scripts/transcribe.py <audio_file> <output_file>

With Options

# Specify model size (default: base)
python3 scripts/transcribe.py audio.mp3 transcript.txt --model medium

# Specify language (improves accuracy)
python3 scripts/transcribe.py audio.mp3 transcript.txt --language zh

# Include timestamps
python3 scripts/transcribe.py audio.mp3 transcript.txt --timestamps

# JSON output with metadata
python3 scripts/transcribe.py audio.mp3 output.json --format json

Parameters

  • audio_file (required): Path to input audio file
  • output_file (required): Path to output text/JSON file
  • --model: Whisper model size (tiny/base/small/medium/large, default: base)
  • --language: Language code (e.g., en, zh, es, fr, auto for detection)
  • --timestamps: Include word-level timestamps in output
  • --format: Output format (text/json, default: text)

Model Sizes

Model Parameters Speed Accuracy Memory
tiny 39M ~32x Good ~1GB
base 74M ~16x Better ~1GB
small 244M ~6x Great ~2GB
medium 769M ~2x Excellent ~5GB
large 1.5B 1x Best ~10GB

Supported Audio Formats

MP3, WAV, M4A, FLAC, OGG, AAC, WMA, and more (via FFmpeg)

Dependencies

  • Python 3.8+
  • openai-whisper
  • ffmpeg

Installation

pip install openai-whisper
sudo apt-get install ffmpeg  # Ubuntu/Debian
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 · 77 lines · 13 tokens per session scan B 8c6d3ac6deb9

Subscribe to this mod's changes

whisper is a skill published in the GitHub repository trpc-group/trpc-agent-go (1,770 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 552 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). 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

meta-short-drama

Use this meta-skill instead of answering directly when the current user asks to generate an AI short-drama or 短剧 from a topic. The workflow infers render style, character identity, and shot count (1-10, default 5) from the request (filling in conservative defaults when missing), drafts a strict shot-by-shot shooting…

opensquilla/opensquilla · 221 tokens

ai-video-script

A tool that turns a topic into a structured short-video shooting plan. Each shot includes prompts for the image and video, spoken narration, and text shown on screen.

opensquilla/opensquilla · 87 tokens

audio-cog

OpenSquilla-compatible audio generation adapter for webpage audio requests. Prefer OpenRouter config/API key in OpenSquilla; preserve the upstream CellCog workflow only as optional ClawHub provenance.

opensquilla/opensquilla · 41 tokens

openrouter-video-generator

Generate or declare an OpenRouter video asset for AwesomeWebpageMetaSkill using a parent-leased Provider Settings connection and configured non-secret model/output values.

opensquilla/opensquilla · 35 tokens

video-still-animator

Turn a single still image (PNG/JPG) into a short MP4 with a slow Ken-Burns zoom and a silent audio track. Pure ffmpeg wrapper. Designed as the onfailure substitute for AI video-gen steps that get blocked by content moderation: when seedance refuses, this skill emits a valid replacement clip from the already-generated…

opensquilla/opensquilla · 88 tokens

nano-banana-pro-openrouter

Deterministic OpenRouter image generation adapter for Nano Banana Pro / Gemini image models. Use as skillexec when a meta-skill needs local image files and structured IMAGEREADY records without spawning an LLM agent.

opensquilla/opensquilla · 49 tokens