stt

stt is a skill for Claude Code, Codex from unclutter-pro/atlas. It costs 21 tokens per session (387 once invoked), scanned A, original, MIT.

A speech-to-text workflow that converts audio or video files into written text using the `stt` command.

In plain words
What is it for?
Use it with WAV, MP3, OGG, M4A, AAC, FLAC, WebM, or MP4 files, or with a recording URL, optionally providing a language hint.
Why use it?
It removes the need to transcribe recordings manually, while noting that noisy audio and multi-speaker conversations can reduce accuracy.

Skill for Claude CodeCodex

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

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/unclutter-pro/atlas/stt
Any agent
npx skills add unclutter-pro/atlas --skill stt
Clone the repo
git clone --depth 1 https://github.com/unclutter-pro/atlas

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 stt

README.md
[![agentmods](https://agentmods.dev/badge/skills/unclutter-pro/atlas/stt.svg)](https://agentmods.dev/skills/unclutter-pro/atlas/stt)
Your own site
<a href="https://agentmods.dev/skills/unclutter-pro/atlas/stt"><img src="https://agentmods.dev/badge/skills/unclutter-pro/atlas/stt.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 387 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00021 $0.00387
Opus 5 $0.00010 $0.00193
Sonnet 5 $0.00004 $0.00077
Haiku 4.5 $0.00002 $0.00039

Measured 5d ago against content hash be3b06ae8796, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

stt scanned grade A 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/stt.sh), 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST "$STT_URL" \
app/defaults/skills/stt/SKILL.md · 53 lines

What it actually says

Speech-to-Text (STT)

Transcribe audio files to text using the stt CLI.

Usage

# Transcribe an audio file
stt /path/to/audio.wav

# Transcribe with language hint
stt --language de /path/to/audio.ogg

# Transcribe from a URL (downloads first)
stt https://example.com/recording.mp3

Supported Formats

wav, mp3, ogg, m4a, aac, flac, webm, mp4 (audio track)

Direct API Usage

The STT endpoint is Whisper-compatible (OpenAI /v1/audio/transcriptions format):

curl -X POST "$STT_URL" \
  -F "file=@/path/to/audio.wav" \
  -F "response_format=json" \
  -F "language=de"

Response: {"text": "transcribed text here"}

The URL is resolved from: ATLAS_STT_URL env → STT_URL env → config.yml (stt.url) → default.

Limitations

  • Long files (>2 min) are split into 120s chunks with 5s overlap — minor artifacts at chunk boundaries are possible
  • Accuracy depends on audio quality; background noise reduces quality significantly
  • The model runs on CPU (int8 quantized) — expect ~5-15s processing per minute of audio
  • Single-speaker optimized; multi-speaker conversations may lose speaker attribution
  • No diarization (speaker identification) — only raw text output

Signal Integration

Audio messages received via Signal are automatically transcribed before reaching the agent — no manual action needed.

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. 5d ago First seen · 53 lines · 21 tokens per session scan A be3b06ae8796

Subscribe to this mod's changes

stt is a skill published in the GitHub repository unclutter-pro/atlas (2 stars, last pushed 17d ago), licensed MIT. It adds 21 tokens to every session and 387 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens