stt
Skill2 starsChanged 4 months agoMITView on GitHub
Transcribe an audio file to text (speech-to-text). Use when the user types "stt" or attaches an audio file (mp3, m4a, wav, flac, aac, ogg, opus, webm, mp4) and asks to "transcribe", "turn this into text", "write this up", or "pull the audio". Uses Deepgram (nova-2) with speaker diarization on by default. Pairs with the `add` skill to file the result.
- Reads credentials
- Installs packages
3 other projects use a version of this.
Adopted by
Most recently taken up by
- magarcia/skillstheir own version, first seen Jul 23, 2026
- verging-ai/agent-skillstheir own version, first seen Jun 8, 2026
- LocalKinAI/kinclawtheir own version, first seen May 12, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- LocalKinAI/kinclaw★ 9same name
- magarcia/skills★ 4same name
- verging-ai/agent-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository9 other files it gives its agents.
- 00_SELF/CLAUDE.mdCLAUDE.md
- 10_WORK/CLAUDE.mdCLAUDE.md
- 20_DOMAINS/CLAUDE.mdCLAUDE.md
- 30_KNOWLEDGE/CLAUDE.mdCLAUDE.md
- 40_SYSTEMS/CLAUDE.mdCLAUDE.md
- 50_LIFE/CLAUDE.mdCLAUDE.md
- 90_SHARED/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- addSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 28
If none was given: *"What's the path to the audio file?"* Handle multiple files in turn.
- Very specific: line 34
Default Korean (ko) unless the filename/context says otherwise (change the default in your fork).
- Very specific: line 54
If the audio was notes/a meeting/a memo worth keeping, hand the transcript to the add skill to route it into the workspace.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
stt — speech to text
Transcribes audio with Deepgram, speaker-labelled, and saves a .txt next to the source.
Setup (once)
Needs a Deepgram API key (generous free tier). Put it in your environment — never in a file the agent might commit:
echo 'export DEEPGRAM_API_KEY="your-key"' >> ~/.zshrc && source ~/.zshrcpip install requests if you don't have it.
Step 1 — get the file path
If none was given: "What's the path to the audio file?" Handle multiple files in turn.
Supported: .mp3 .m4a .wav .flac .aac .mp4 .ogg .webm .opus
Step 2 — language
Default Korean (ko) unless the filename/context says otherwise (change the default
in your fork). If unclear, ask briefly.
Step 3 — run
python3 ~/.claude/skills/stt/transcribe.py "<path>" --lang <code>Options: --lang en (or ko, es, …) · --no-diarize (single speaker, faster) ·
--model nova-2.
Quote paths that contain spaces.
Step 4 — output
Print the transcript to the conversation. It's also saved as <path>.txt.
Step 5 — file it (optional)
If the audio was notes/a meeting/a memo worth keeping, hand the transcript to the add
skill to route it into the workspace. Remember add's rule: cross-check transcribed
names against people.md — STT mangles proper nouns.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

