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 tallesborges/zdx --skill transcriptiongit clone --depth 1 https://github.com/tallesborges/zdxWrote 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/tallesborges/zdx/transcription)<a href="https://agentmods.dev/skills/tallesborges/zdx/transcription"><img src="https://agentmods.dev/badge/skills/tallesborges/zdx/transcription/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/tallesborges/zdx/transcription"><img src="https://agentmods.dev/badge/skills/tallesborges/zdx/transcription.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Excessive Agency · line 51 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- high Excessive Agency · line 68 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00067 | $0.01086 |
| Opus 5 | $0.00034 | $0.00543 |
| Sonnet 5 | $0.00013 | $0.00217 |
| Haiku 4.5 | $0.00007 | $0.00109 |
Grade A, and why
transcription scanned grade A with 0 findings 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 11d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Transcription – Speech-to-Text via zdx transcribe
Turn an audio file into text using ZDX's native zdx transcribe command. The transcript is printed to stdout.
Only use this skill when the user explicitly points at a specific audio file to transcribe on demand. Incoming Telegram voice notes and the TUI voice-dictation hotkey are already transcribed automatically — don't use this skill for those.
CLI reference
zdx transcribe <FILE> [OPTIONS]
Options:
--model <MODEL> provider:model id (e.g. elevenlabs:scribe_v2, mistral:voxtral-mini-latest)
or a bare provider name (openai, mistral, xai, elevenlabs) for its default
--language <LANG> Language hint, ISO 639-1 (e.g. en, pt)
--diarize Label speakers (Mistral/Voxtral or ElevenLabs only)
--json Emit JSON (text + diarized segments) instead of plain text
--list-models List the supported transcription models (with --json for machine output)
Output: prints the transcript text to stdout (nothing else). If no provider is configured, it prints a short "no provider" notice to stderr and exits without transcribing.
Using the transcript
The output is text, not audio — read it from stdout and use it directly in your reply (quote it, summarize it, or act on it as asked). Do not wrap it in a <media> tag; that tag is only for sending audio/image files back.
zdx transcribe "$ZDX_ARTIFACT_DIR/note.ogg"
Providers
- Auto-detect order: OpenAI → Mistral → xAI → ElevenLabs. OpenAI uses
whisper-1(OPENAI_API_KEY); Mistral usesvoxtral-mini-latest(MISTRAL_API_KEY); xAI usesgrok-stt(XAI_API_KEY); ElevenLabs usesscribe_v2(ELEVENLABS_API_KEY). This is the reverse ofzdx speak, which prefers Mistral. - Run
zdx transcribe --list-modelsto see the supported models and which have an API key configured. - To pick a specific provider, pass
--model <provider>(default model) or--model <provider>:<model>(exact model). There is no separate--providerflag. - Voxtral and ElevenLabs Scribe v2 both support speaker diarization (
--diarize); OpenAIwhisper-1and xAI do not. ElevenLabs Scribe v2 is state-of-the-art accuracy across 90+ languages;whisper-1is a solid general default.
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.
- 11d ago First seen · 76 lines · 67 tokens per session scan A d65a52f496e5
transcription is a skill published in the GitHub repository tallesborges/zdx (20 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 1,086 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.