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 olegvg/olegvg-skills --skill transcribing-audiogit clone --depth 1 https://github.com/olegvg/olegvg-skillsWrote 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/olegvg/olegvg-skills/transcribing-audio)<a href="https://agentmods.dev/skills/olegvg/olegvg-skills/transcribing-audio"><img src="https://agentmods.dev/badge/skills/olegvg/olegvg-skills/transcribing-audio/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/olegvg/olegvg-skills/transcribing-audio"><img src="https://agentmods.dev/badge/skills/olegvg/olegvg-skills/transcribing-audio.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 | $0.00077 | $0.01021 |
| Opus 5 | $0.00039 | $0.00511 |
| Sonnet 5 | $0.00015 | $0.00204 |
| Haiku 4.5 | $0.00008 | $0.00102 |
Grade A, and why
transcribing-audio 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 12d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Transcribing Audio
Safety and privacy
- Resolve the input and output paths without copying audio into the repository.
- Keep audio local by default. Never infer permission to upload it: before OpenAI mode, explain that audio chunks leave the machine and obtain explicit consent.
- Never print dotenv values or commit audio, transcripts, runtime state, or model caches.
- Treat raw diarization labels as labels, not identities. Apply
--speaker-namesonly after diarization returns those raw labels.
Choose the mode
- Use local ASR when the user requires local processing or has not explicitly approved an upload.
- Use OpenAI ASR only after explicit consent. Every TTY run asks for local/OpenAI even when
--modesupplies a default; a non-TTY OpenAI run requires--allow-cloud-upload. - Select
--speakers Nfor an exact count,--min-speakerswith optional--max-speakersfor a range, or omit speaker flags for automatic diarization.
Run the pipeline
Set SKILL_DIR from the absolute directory containing this loaded SKILL.md; do not derive it from the shell working directory or $0.
SKILL_DIR="<absolute path to this skill directory>"
"$SKILL_DIR/../../scripts/transcribe_audio.py" --help
Run the launcher from that resolved path. Use --resume after an interruption; it validates and reuses prior committed stages. Canonical JSON is authoritative; TXT, SRT, and VTT are derived only after the JSON validates.
Stop conditions
- Stop before any upload if consent is absent, declined, or ambiguous.
- Stop and report the exact failed intervals if the one allowed quality retry remains unresolved. Do not present derived output as successful.
- Stop on unsafe paths, missing prerequisites, failed local model access, or a provider failure; report the redacted error and the safe recovery option.
Common commands
Replace the placeholders with real paths. The first command is interactive; every TTY run still asks for input, mode, and speaker policy.
What ships with it
7 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.
- 12d ago First seen · 81 lines · 77 tokens per session scan A 48f9e2fa26a2
transcribing-audio is a skill published in the GitHub repository olegvg/olegvg-skills (7 stars, last pushed 2mo ago), licensed MIT. It adds 77 tokens to every session and 1,021 once invoked, about $0.0004 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 2026-08-31.
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).
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.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.