Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/thewolffish/wolffish-app/speech-to-text)<a href="https://agentmods.dev/skills/thewolffish/wolffish-app/speech-to-text"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/speech-to-text/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.
<a href="https://agentmods.dev/skills/thewolffish/wolffish-app/speech-to-text"><img src="https://agentmods.dev/badge/skills/thewolffish/wolffish-app/speech-to-text.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.02932 |
| Opus 5 | $0.00034 | $0.01466 |
| Sonnet 5 | $0.00014 | $0.00586 |
| Haiku 4.5 | $0.00007 | $0.00293 |
Grade B, and why
speech-to-text 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 5d 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.
- Everything is provisioned managed-first with no admin rights. Do NOT propose `sudo apt` / `brew` / `winget` installs for speech-to-text. How it starts
The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Speech-to-text
Interface
- Tools:
stt_transcribe,stt_transcribe_upload,stt_transcribe_voice_memo,stt_detect_language - Engine: faster-whisper (CTranslate2 + PyAV) — free, open-source, 100% local, and far lighter than reference Whisper (no PyTorch, no external ffmpeg).
- Models: tiny → base → small → medium → large (accuracy vs. speed tradeoff)
- Setup: fully automatic — the
pythoncapability provisions a hermetic Python runtime and installs faster-whisper into an isolated venv on first use (no host Python and no ffmpeg required). The chosen model is downloaded on first use.
When to use each tool
Never transcribe the user's own voice note. When the user's message is tagged
<voice_note>, it was ALREADY transcribed before the agent ran — the visible message text IS the transcript. The audio attached to that message is only the source of that transcript. Do NOT call anystt_*tool on it; just respond to the text (per the<voice_prompts>rules in your prompt). These tools are for a separate audio file the user hands you to transcribe — not for their own spoken message.
-
"transcribe this", "what does this audio say?", "what did they say?" with an uploaded audio file →
stt_transcribe_uploadusing the uploaded file's name. The<attachments>block in the user message lists every uploaded filename and type. -
"transcribe the last voice memo", "transcribe what you just said" →
stt_transcribe_voice_memowith the filename from the most recent text-to-speech tool result. -
User provides an absolute path: "transcribe /Users/me/recording.wav" →
stt_transcribewith that path. -
"what language is this?", "what language are they speaking?" →
stt_detect_languagereturns the language without a full transcription. -
"my voice notes come out in the wrong language", "transcribe in Arabic from now on", "use a more accurate model" → the settings tools below. This is yours to fix, not something to send the user to Settings for.
What ships with it
2 files 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.
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.
- 5d ago Changed · +62 lines 6d43de87264f
- 10d ago First seen · 192 lines · 68 tokens per session scan B 892b017a52ce
speech-to-text is a skill published in the GitHub repository thewolffish/wolffish-app (5 stars, last pushed 4d ago), licensed MIT. It adds 68 tokens to every session and 2,932 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
agent-computer-use
REQUIRED for any task that involves operating a desktop application — opening apps, clicking buttons, typing into fields, pressing keys, scrolling, dragging, reading what's on screen, moving or resizing windows, or verifying state after an action. Always use the agent-cu CLI commands (open, snapshot, click, type, key…
claude-api
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…
create-skill
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
figma-create-design-system-rules
Generates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server…
figma-generate-design
Use this skill alongside figma-use when the task involves translating an application page, view, or multi-section layout into Figma. Triggers: 'write to Figma', 'create in Figma from code', 'push page to Figma', 'take this app/page and build it in Figma', 'create a screen', 'build a landing page in Figma', 'update the…
figma-generate-library
Build or update a professional-grade design system in Figma from a codebase. Use when the user wants to create variables/tokens, build component libraries, set up theming (light/dark modes), document foundations, or reconcile gaps between code and Figma. This skill teaches WHAT to build and in WHAT ORDER — it…