vivadicta-transcribe-flow

vivadicta-transcribe-flow is a skill for Claude Code, Codex from n0an/vivadicta-cli-skills. It costs 56 tokens per session (1,556 once invoked), scanned A, original, MIT.

A workflow for turning a local audio file or YouTube video into a searchable VivaDicta transcription.

In plain words
What is it for?
Transcribing local recordings or YouTube URLs and saving the resulting speech text in VivaDicta history.
Why use it?
It handles source detection, waiting for transcription jobs, progress checks, and recovery from errors.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/you/Downloads/meeting.m4a.

Good fit Transcribing local recordings or YouTube URLs and saving the resulting speech text in VivaDicta history.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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.

agentmods badge for vivadicta-transcribe-flow

README.md
[![agentmods](https://agentmods.dev/badge/skills/n0an/vivadicta-cli-skills/vivadicta-transcribe-flow/github.svg)](https://agentmods.dev/skills/n0an/vivadicta-cli-skills/vivadicta-transcribe-flow)
Your own site
<a href="https://agentmods.dev/skills/n0an/vivadicta-cli-skills/vivadicta-transcribe-flow"><img src="https://agentmods.dev/badge/skills/n0an/vivadicta-cli-skills/vivadicta-transcribe-flow/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.

agentmods 80×15 button for vivadicta-transcribe-flow

Your own site · 80×15
<a href="https://agentmods.dev/skills/n0an/vivadicta-cli-skills/vivadicta-transcribe-flow"><img src="https://agentmods.dev/badge/skills/n0an/vivadicta-cli-skills/vivadicta-transcribe-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,556 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.01556
Opus 5 $0.00028 $0.00778
Sonnet 5 $0.00011 $0.00311
Haiku 4.5 $0.00006 $0.00156

Measured 11d ago against content hash 75433e192b97, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

vivadicta-transcribe-flow 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.

skills/vivadicta-transcribe-flow/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

vivadicta transcribe flow

Use this skill to turn an audio file or a YouTube URL into a searchable transcription in the user's VivaDicta history. Covers input-shape detection, blocking vs --async, progress output, and recovery paths.

Preconditions

  • VivaDicta.app installed at /Applications/VivaDicta.app and running (writes require the UI).
  • User has a transcription model configured (Whisper local, Parakeet local, or a cloud provider with API key in Keychain).
  • For YouTube URLs, the app's YouTube transcription is enabled (one of: captions → Apify → yt-dlp → Whisper).

Pick the source and invocation

# Local file, blocking (default) - waits until done, prints the final transcription summary
vivadicta transcribe ~/Downloads/meeting.m4a

# YouTube URL, blocking
vivadicta transcribe "https://youtu.be/dQw4w9WgXcQ"

# Either source, async - returns the job UUID immediately
vivadicta transcribe ~/Downloads/meeting.m4a --async

Input auto-routes:

Input shape Routes to
http:// / https:// prefix transcribe_url (YouTube)
file:// prefix strip scheme, treat as path
Absolute path (/...), ~/..., ./, ../, or a bare filename that resolves against CWD transcribe_file
- (stdin) rejected (not supported in v1)

Ambiguous or nonexistent paths exit 2 with a clear message.

Blocking vs async

Blocking (default): the command waits up to VIVADICTA_TIMEOUT_SECONDS (default 600) polling every 2 s, then prints the full transcription summary on stdout (same shape as vivadicta get). Progress phase lines stream to stderr: [vivadicta] downloading captions… / [vivadicta] transcribing (parakeet)… / [vivadicta] enhancing (claude)….

Prefer blocking when:

  • The next step in the user's request needs the transcript (rewrite, grep, summarize).
  • The audio is short (<1 min) or the transcription model is local.

Async (--async): returns a job UUID immediately. Poll with vivadicta job <uuid> when you want status.

Read the full file on GitHub · 122 lines

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.

  1. 11d ago First seen · 122 lines · 56 tokens per session scan A 75433e192b97

Subscribe to this mod's changes

vivadicta-transcribe-flow is a skill published in the GitHub repository n0an/vivadicta-cli-skills (6 stars, last pushed 4mo ago), licensed MIT. It adds 56 tokens to every session and 1,556 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.

Related

Other skills, from other repositories