What is whisper-transcribe?

A tool for turning speech in local audio or video files into written text. It can produce plain text, subtitle files, or a formatted transcript, and can record details about the processed files.

Use it to transcribe recordings, create captions or subtitles, convert speech to text, or process several local media files.

It removes the need to type recordings by hand and gives you standard files for reading, editing, or adding subtitles.

whisper-transcribe — Skill for Claude Code by fabioespindula

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/fabioespindula/awesome-nanoclaw-skills

agentmods

npx agentmods add skills/fabioespindula/awesome-nanoclaw-skills/whisper-transcribe

Made for: Claude Code.

Its marketplace also offers this one on its own, as the plugin whisper-transcribe — /plugin install whisper-transcribe after adding the marketplace above.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fabioespindula/awesome-nanoclaw-skills/whisper-transcribe/github.svg)](https://agentmods.dev/skills/fabioespindula/awesome-nanoclaw-skills/whisper-transcribe)

Your own site

<a href="https://agentmods.dev/skills/fabioespindula/awesome-nanoclaw-skills/whisper-transcribe"><img src="https://agentmods.dev/badge/skills/fabioespindula/awesome-nanoclaw-skills/whisper-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fabioespindula/awesome-nanoclaw-skills/whisper-transcribe"><img src="https://agentmods.dev/badge/skills/fabioespindula/awesome-nanoclaw-skills/whisper-transcribe.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,038 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00068	$0.02038
Opus 5	$0.00034	$0.01019
Sonnet 5	$0.00014	$0.00408
Haiku 4.5	$0.00007	$0.00204

Measured 12d ago against content hash 3f296d81c368, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

whisper-transcribe 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.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/setup-host.sh, scripts/validate-whisper-transcribe.sh, scripts/whisper_transcribe.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/whisper-transcribe/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Whisper Transcribe

Use this skill to transcribe local audio or video files with faster-whisper.

Managed Auto Update

If this skill is installed as a managed Awesome NanoClaw Skill and ../awesome-updater/scripts/awesome_skills.py exists, run this before the normal workflow:

python3 ../awesome-updater/scripts/awesome_skills.py check awesome-updater --skills-dir .. || true
python3 ../awesome-updater/scripts/awesome_skills.py discover --skills-dir .. || true
python3 ../awesome-updater/scripts/awesome_skills.py check whisper-transcribe --skills-dir .. || true

Continue the normal workflow if the update or discover check fails because of network, GitHub, or local environment issues.

Triggers

Run this skill when the user asks to:

transcribe a local audio or video file
create captions or subtitles from a local file
create txt, srt, or vtt transcript output
convert a local recording to text
"transcribe this audio", "generate captions", or equivalent intent

If the user does not provide a local file path and no attached file path is available in the conversation, ask one short question for the path.

Help Mode

If the user invokes /whisper-transcribe help, /whisper-transcribe examples, or asks how to use this skill, explain usage instead of transcribing media.

The help response should include:

what Whisper Transcribe does;
when to use it;
dependency requirements;
command forms: /whisper-transcribe <local-file>, mode-specific variants, /nanoskills help whisper-transcribe, doctor, and host setup checks;
what input the user should provide;
what output the user gets;
curated examples;
contextual examples when the visible conversation includes a useful local media path, language, meeting, caption, or archive goal.

Curated examples:

/whisper-transcribe /absolute/path/to/audio.mp3
/whisper-transcribe /absolute/path/to/video.mp4 --mode captions
/whisper-transcribe Transcribe this audio and generate SRT. /absolute/path/audio.m4a

Read the full file on GitHub · 207 lines

Files

What ships with it

14 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.

Changes

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 · 207 lines · 68 tokens per session scan A 3f296d81c368

Subscribe to this mod's changes

whisper-transcribe is a skill published in the GitHub repository fabioespindula/awesome-nanoclaw-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 68 tokens to every session and 2,038 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 2026-08-31.

Claude Code Documents agent-skills ai-agents ai-assistent awesome-list mcp

gdoc-to-markdown

Internal fetcher module for Google Docs and Sheets. Fetches content via MCP (preferred, when available), Google API with bearer token or public URL export (fallback), or browser DOM extraction via Claude in Chrome (last resort) and returns Markdown. Used by /bedrock:teach and /bedrock:sync — not intended for direct…

ccplugins/awesome-claude-code-plugins · 76 tokens

confluence-to-markdown

Internal fetcher module for Confluence pages. Fetches content via Atlassian MCP (preferred), REST API with Basic Auth (fallback), or browser DOM extraction via Claude in Chrome (last resort) and returns Markdown. Used by /bedrock:teach and /bedrock:sync — not intended for direct user invocation.

ccplugins/awesome-claude-code-plugins · 71 tokens

pdf-processing

Inspect, extract, OCR, create, merge, split, reorder, rotate, annotate, fill, redact, compress, secure, and verify PDF documents while preserving source files and visual fidelity. Use when working with one or more .pdf files; converting documents to or from PDF; extracting text, tables, images, metadata, forms, or…

seb1n/awesome-ai-agent-skills · 105 tokens

spreadsheet-analysis

Inspect, profile, clean, reconcile, analyze, visualize, and verify spreadsheet data while preserving formulas, formatting, types, and source files. Use when working with .xlsx, .xlsm, .xls, .ods, .csv, or .tsv files; answering questions from a workbook; auditing formulas or data quality; comparing sheets or versions…

seb1n/awesome-ai-agent-skills · 102 tokens

summarization

Summarize text using extractive, abstractive, hierarchical, and multi-document techniques, producing concise outputs at configurable detail levels. Use when the user requests summarization or provides relevant inputs for this workflow.

seb1n/awesome-ai-agent-skills · 45 tokens

technical-writing

Write clear, concise, and accurate technical documentation including API references, user guides, tutorials, changelogs, and architecture docs, tailored to the target audience. Use when the user requests technical writing or provides relevant inputs for this workflow.

seb1n/awesome-ai-agent-skills · 50 tokens