What is local-media-transcription?

A local transcription tool for turning audio and video files into timestamped text and subtitle files. It uses the Whisper large-v3 speech-recognition model on an NVIDIA GPU when available, with local CPU fallbacks.

Use it for meeting recordings, interviews, presentations, and internal calls, producing .txt and .srt files.

It keeps recordings and transcripts off external services while handling cases where the GPU is unavailable or has limited memory.

local-media-transcription — Skill by rumotion

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/rumotion/ai-agent-project-template

agentmods

npx agentmods add skills/rumotion/ai-agent-project-template/local-media-transcription

Made for: Claude Code, Codex.

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/rumotion/ai-agent-project-template/local-media-transcription/github.svg)](https://agentmods.dev/skills/rumotion/ai-agent-project-template/local-media-transcription)

Your own site

<a href="https://agentmods.dev/skills/rumotion/ai-agent-project-template/local-media-transcription"><img src="https://agentmods.dev/badge/skills/rumotion/ai-agent-project-template/local-media-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rumotion/ai-agent-project-template/local-media-transcription"><img src="https://agentmods.dev/badge/skills/rumotion/ai-agent-project-template/local-media-transcription.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 558 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	$0.00062	$0.00558
Opus 5.5	$0.00025	$0.00223
Sonnet 5.5	$0.00012	$0.00112
Haiku 4.5	$0.00006	$0.00056

Measured 13d ago against content hash 7032cfd10e20, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

local-media-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 13d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/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.

.agents/skills/local-media-transcription/SKILL.md · 48 lines

What it actually says

Local Media Transcription (GPU-First)

Use this skill whenever you need to transcribe audio or video recordings (e.g. meeting recordings, interviews, technical presentations, internal calls) in any project on this machine.

Standing Rules & Constraints

GPU-First (NVIDIA RTX A5000): Always execute transcription on CUDA via faster-whisper (CTranslate2).
Model Constraint: Always use large-v3 (32 layers). Never substitute turbo, small, base, or medium. Proper-noun fidelity (vendor names, model names, people) is mandatory.
100% Local & Confidential: No audio, video, or transcripts may be sent to any external service or API.
Precision Fallback Ladder:
- Tier 1: CUDA float16 (Default, ~4.0 GB VRAM, ~5x real-time speedup)
- Tier 2: CUDA int8_float16 (Fallback on VRAM pressure, ~2.8 GB VRAM)
- Tier 3: CPU chunked parallel (Emergency fallback if CUDA is unavailable)

How to Transcribe

Run the bundled transcription script on your target media file:

python .agents/skills/local-media-transcription/scripts/transcribe.py "<media-file>" [output-dir]

Or pass the direct path:

python scripts/transcribe_local_large_v3.py "<media-file>" [output-dir]

Outputs

<output-dir>/<stem>_large-v3.txt (Timestamped format: [HH:MM:SS] text)
<output-dir>/<stem>_large-v3.srt (Standard SRT subtitle format with millisecond precision)

Technical Details

Language Detection: Detects language once on the first 30 seconds using tiny and forces the detected language on large-v3 to prevent per-segment mis-detection.
Audio Extraction: Uses ffmpeg -vn -ac 1 -ar 16000 -c:a pcm_s16le for clean 16kHz mono audio.
Speech Conditioning: Sets condition_on_previous_text=False and vad_filter=False to prevent clipping quiet words or hallucinating across silence boundaries.

Files

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.

scripts/transcribe.py 12 KB runs code

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.

13d ago First seen · 48 lines · 62 tokens per session scan A 7032cfd10e20

Subscribe to this mod's changes

local-media-transcription is a skill published in the GitHub repository rumotion/ai-agent-project-template (1 stars, last pushed 13d ago), licensed MIT. It adds 62 tokens to every session and 558 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-04.

Writing and docs ai-assisted-coding boilerplate cline google-antigravity memory-bank

saas-builder

Clone, verify, map, and build on top of ixartz/SaaS-Boilerplate for a user's SaaS idea. Use when a user wants to reuse SaaS Boilerplate, evaluate how their product fits it, or build product-specific pages, database schema, roles, permissions, MVP features, and launch scope on top of the boilerplate.

ixartz/SaaS-Boilerplate · 75 tokens

dashboard-builder

Build self-contained interactive HTML dashboards with charts, filters, and tables. Generates a single browser-openable file — no server or dependencies required.

winstonkoh87/Athena-Public · 31 tokens

bionic-decision-engine

Unified mathematical arbitrator for all resource allocation decisions — money, time, energy, relationships. Absorbs 46 decision protocols + 24 strategy protocols into one dense engine.

winstonkoh87/Athena-Public · 41 tokens

trading-risk-gate

Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.

winstonkoh87/Athena-Public · 53 tokens

skill-creator-primer

You MUST load this skill before the skill-creator skill AND before making ANY change to, or conducting a review of ANY Agent Skill. Triggers include creating, editing, reviewing, or contributing to any part of an Agent Skill (description, frontmatter, body, references, scripts, trigger evals, conflicts, etc).

sammcj/agentic-coding · 74 tokens

database-patterns

DB schema design and query tuning: normalization, indexing, N+1, transactions, EXPLAIN. Triggers: schema, index, slow query, N+1, PostgreSQL, MySQL, EXPLAIN, deadlock, query plan.

softspark/ai-toolkit · 55 tokens