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 allenhutchison/obsidian-gemini --skill audio-transcriptiongit clone --depth 1 https://github.com/allenhutchison/obsidian-geminiWrote 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/allenhutchison/obsidian-gemini/audio-transcription)<a href="https://agentmods.dev/skills/allenhutchison/obsidian-gemini/audio-transcription"><img src="https://agentmods.dev/badge/skills/allenhutchison/obsidian-gemini/audio-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/allenhutchison/obsidian-gemini/audio-transcription"><img src="https://agentmods.dev/badge/skills/allenhutchison/obsidian-gemini/audio-transcription.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.00631 |
| Opus 5 | $0.00021 | $0.00316 |
| Sonnet 5 | $0.00008 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
audio-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 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audio & Video Transcription
Transcribe audio and video files from the vault into structured Obsidian notes using read_file to send binary media directly to the model.
Supported Formats
Audio: .wav, .mp3, .aac, .flac, .webm (audio-only)
Video: .mp4, .mpeg, .mov, .flv, .mpg, .webm, .wmv, .3gp
Size limit: 20 MB per file (Gemini inline data limit).
How to Transcribe
- Use
read_filewith the path to the audio/video file — the binary data is sent directly to the model for processing. - Listen to/watch the content and produce a transcription.
- Use
write_fileto save the transcription as a markdown note.
Transcription Format
Structure transcriptions as follows:
---
tags:
- transcription
source: "[[original-file.mp3]]"
date: YYYY-MM-DD
duration: "MM:SS" (estimate if possible)
---
# Transcription: [Title]
## Summary
Brief 2-3 sentence summary of the content.
## Transcript
[00:00] Speaker 1: Opening remarks...
[00:45] Speaker 2: Response...
[01:30] Speaker 1: Follow-up...
Guidelines
- Timestamps: Include approximate timestamps in
[MM:SS]format at natural breaks (new speakers, topic changes, pauses). - Speaker identification: Label distinct speakers as "Speaker 1", "Speaker 2", etc. If names are mentioned, use them after first identification.
- Filler words: Omit excessive filler words (um, uh, like) unless they carry meaning.
- Inaudible sections: Mark unclear audio as
[inaudible]or[unclear]. - Non-speech sounds: Note significant sounds like
[laughter],[applause],[music]. - Summary: Always include a brief summary at the top for quick reference.
- Frontmatter: Link back to the source file using a wikilink.
Tips
- For long recordings, let the user know the transcription may be partial due to the 20 MB size limit. Suggest splitting large files with an external tool.
- If the user asks to "transcribe the recording in this note", use
read_fileon the current note first to find embedded audio/video links (e.g.,![[recording.mp3]]), thenread_fileon the linked file. - For meeting notes, suggest adding attendees and action items sections after the transcript.
- For podcasts or interviews, suggest adding a "Key Topics" section with timestamps.
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 · 67 lines · 42 tokens per session scan A 5c83edcc0566
audio-transcription is a skill published in the GitHub repository allenhutchison/obsidian-gemini (524 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 631 once invoked, about $0.0002 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
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.