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.
npx skills add lkmeta/txtify --skill txtify-transcribegit clone --depth 1 https://github.com/lkmeta/txtifyWrote 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/lkmeta/txtify/txtify-transcribe)<a href="https://agentmods.dev/skills/lkmeta/txtify/txtify-transcribe"><img src="https://agentmods.dev/badge/skills/lkmeta/txtify/txtify-transcribe/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/lkmeta/txtify/txtify-transcribe"><img src="https://agentmods.dev/badge/skills/lkmeta/txtify/txtify-transcribe.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 | $0.00088 | $0.04829 |
| Opus 5.5 | $0.00035 | $0.01932 |
| Sonnet 5.5 | $0.00018 | $0.00966 |
| Haiku 4.5 | $0.00009 | $0.00483 |
Grade A, and why
txtify-transcribe 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 today.
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.
| Terminal | run `curl` and `docker` | always (else use the browser fallback) | How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Txtify transcribe
Txtify is a free, open-source (Apache-2.0) web app that transcribes audio and video with OpenAI's Whisper models (via stable-ts) and exports txt, srt, vtt, sbv and pdf. It runs as one Docker container on port 8011. This skill drives a Txtify instance on the user's own machine through the same HTTP endpoints its web page uses.
Project: https://github.com/lkmeta/txtify · Website and live demo: https://txtify.lkmeta.com
What this skill does and does not do
- Does: local file or single YouTube video → transcript/subtitles, choice of Whisper model and spoken language, optional DeepL translation, save results where the user says.
- Does not: speaker diarization, live/microphone transcription, batch folders, or playlists. Txtify has no documented, versioned public API: the endpoints below are the ones its own web page calls. If a call returns something this skill does not describe, stop and use the browser fallback.
- Never sends media to the public website. https://txtify.lkmeta.com is a live demo of how Txtify works (the site itself says to self-host for real, private transcription), so it's no place for the user's files.
Access this skill needs
Ask before each item that is not already allowed in this session.
| Access | Why | When |
|---|---|---|
| Terminal | run curl and docker |
always (else use the browser fallback) |
http://127.0.0.1:8011 |
talk to the local Txtify | always |
| Docker + Docker Hub | pull lkmeta/txtify (about 2-3 GB) and run it |
only if Txtify isn't running |
| Read the chosen media file | upload it to the local Txtify | per job |
| Write to a folder the user picks | save the exports | per job |
| Internet from the container | Whisper weights download on first use of each model (tiny about 75 MB, large about 3 GB); YouTube download for URL jobs; DeepL only if translation is on | see step 3 |
What leaves the machine: YouTube URL jobs fetch the video from YouTube. Translation sends the transcript text to DeepL with the user's key. Model weights are downloaded once. Transcription itself (Whisper) runs locally. Nothing is sent to Agensi or to the skill author.
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.
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.
- today First seen · 239 lines · 88 tokens per session scan A dc89ca0292f8
txtify-transcribe is a skill published in the GitHub repository lkmeta/txtify (135 stars, last pushed today), licensed Apache-2.0. It adds 88 tokens to every session and 4,829 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-28.
Other skills, from other repositories
faster-whisper
Local speech-to-text using faster-whisper. 4-6x faster than OpenAI Whisper with identical accuracy; GPU acceleration enables 20x realtime transcription. SRT/VTT/TTML/CSV subtitles, speaker diarization, URL/YouTube input, batch processing with ETA, transcript search, chapter detection, per-file language map.
audio-transcriber-transcription
Speech-to-text on the audio-transcriber MCP server — run Whisper (faster-whisper, falling back to openai-whisper) over a local audio/video file or a microphone recording, and export txt/srt/vtt/json captions. Use when the agent must transcribe or translate spoken audio, generate subtitle/caption files, or pick a…
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…
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…
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…
audio-transcriber
Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration.