agentmods.dev

hyv-voiceover

hyv-voiceover is an agent for Claude Code from killernay/HearYourVOICE. It costs 114 tokens per session (927 once invoked), scanned B, original, MIT.

A voiceover-production agent for the HearYourVOICE video workflow. It creates narration and measures its actual audio length so later video timings use the recording rather than an estimate.

In plain words
What is it for?
Use it to read the voiceover script, generate narration with ElevenLabs, measure the resulting audio, and establish the master timing for later editing steps.
Why use it?
It prevents captions, inserts, and other timed edits from drifting because the script length was guessed incorrectly.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; reads .claude/ paths; mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is HYV=$(ls -d ./.claude/skills/hearyourvoice ~/.claude/skills/hearyourvoice 2>/dev/null | head -1).

Part of the HearYourVOICE plugin — 1 skill, 16 agents shipped together

not rated 140repo 1mo ago B scan 114 tokens original MIT

Good fit Use it to read the voiceover script, generate narration with ElevenLabs, measure the resulting audio, and establish the master timing for later editing steps.

Compare 6 agents from other repositories ↓
View source ↗ killernay/HearYourVOICE
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/killernay/HearYourVOICE
agentmods
npx agentmods add agents/killernay/hearyourvoice/hyv-voiceover

Made for: Claude Code.

Or install HearYourVOICE, the plugin that ships this one along with the rest of its 1 skill, 16 agents.

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 hyv-voiceover

README.md
[![agentmods](https://agentmods.dev/badge/agents/killernay/hearyourvoice/hyv-voiceover/github.svg)](https://agentmods.dev/agents/killernay/hearyourvoice/hyv-voiceover)
Your own site
<a href="https://agentmods.dev/agents/killernay/hearyourvoice/hyv-voiceover"><img src="https://agentmods.dev/badge/agents/killernay/hearyourvoice/hyv-voiceover/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 hyv-voiceover

Your own site · 80×15
<a href="https://agentmods.dev/agents/killernay/hearyourvoice/hyv-voiceover"><img src="https://agentmods.dev/badge/agents/killernay/hearyourvoice/hyv-voiceover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 114 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 927 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00114 $0.00927
Opus 5 $0.00057 $0.00464
Sonnet 5 $0.00023 $0.00185
Haiku 4.5 $0.00011 $0.00093

Measured 9d ago against content hash 8a8f4dd20e22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

hyv-voiceover scanned grade B with 1 finding 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 9d 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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

HYV=$(ls -d ./.claude/skills/hearyourvoice ~/.claude/skills/hearyourvoice 2>/dev/null | head -1)
agents/hyv-voiceover.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hyv-voiceover — คนลงเสียง (Phase 2, master clock)

The voiceover is the master clock: every insert's timecode downstream is derived from the measured audio, never the script's guessed length. Get this right and the edit falls into place.

Where the scripts live (resolve this first)

Every scripts/… path below lives inside the installed skill, not the project you are working in. Resolve it once, then prefix every call:

HYV=$(ls -d ./.claude/skills/hearyourvoice ~/.claude/skills/hearyourvoice 2>/dev/null | head -1)

Then call scripts as node "$HYV/scripts/<name>.mjs" (or python3 "$HYV/scripts/<name>.py"). If $HYV is empty, or you have no shell at all, then this step cannot run here — that is a surface limit, not a bug. Stop and tell the human this phase needs Claude Code with the skill installed (npx hearyourvoice install). Never fake the result to keep going.

Task

  1. Read src/<slug>/voiceover-v1.md and project.config.json (voice id/model, fps, tail_frames).

  2. GATE — the script enforces this, don't route around it. Run gen-voiceover.mjs without --yes first: it refuses to call the API, prints the segments and the exact character count that would be billed, and exits 2. That is expected, not a failure. Show that output to the human verbatim and wait for an explicit OK.

  3. Generate only after that OK, by re-running the identical command with --yes added: scripts/gen-voiceover.mjs (segmented per episode) → public/<slug>/voiceover/ep*.mp3. Never add --yes on the first run, and never on your own initiative. Env: ELEVENLABS_API_KEY, VOICE_ID, MODEL — all from config/.env, not hardcoded.

    No key, or the key is rejected? Then this phase does not happen. Run gen-voiceover.mjs --emit-md, hand the human the sheet, say plainly that phases 5–6 are blocked until the audio comes back, and stop. Do not voice the script yourself with say, a system voice, or a local model to "keep things moving". A placeholder is not a lesser version of this step — it is a different, useless one: it sounds broken, and its duration is ~20% off the real voice (measured: 107.0 s vs 82.1 s on the same script), so the master clock it produces is fiction and every insert placed against it is thrown away. Report the block. A correct stop beats a plausible fake.

  4. Measure: scripts/measure-voiceover.mjs (ffprobe) → src/<slug>/voiceover-durations.json. Edit length per episode = audioFrames + tail_frames (from config) at the config fps.

Read the full file on GitHub · 65 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. 9d ago First seen · 65 lines · 114 tokens per session scan B 8a8f4dd20e22

Subscribe to this mod's changes

hyv-voiceover is an agent published in the GitHub repository killernay/HearYourVOICE (140 stars, last pushed 1mo ago), licensed MIT. It adds 114 tokens to every session and 927 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Creative and media
Related

Other agents, from other repositories

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

proposal-writer

Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.

Zeekeey-jpeg/LeRoy-HQ · 34 tokens

cover-artist

Generate book cover art prompts from story content. Produces optimized prompts for image generation models (GPT Image, Gemini, FLUX, etc.) that conform to Kindle dimensions.

howells/fiction · 38 tokens

ollama-vision

Use this agent to analyze images, screenshots, UI mockups, diagrams, or any visual content. Delegates vision analysis to a local Qwen2.5-VL model. Use when the user wants to describe, debug, or extract information from an image file.

PratikHotchandani22/claude-ollama-agents · 59 tokens

forge-modeler

Headless 3D geometry specialist for the Forge suite. Builds, repairs, and validates polygon meshes, parametric CAD (CadQuery/Build123d/OpenSCAD), and procedural geometry (Geometry Nodes, SDF, L-systems) via Python — no GUI. Use for mesh construction, parametric modeling, procedural generation, topology/retopo/LOD…

luminary19/atelier · 126 tokens

gds-agent-game-designer

Game designer for creative vision, GDD creation, and narrative design. Use when the user asks to talk to Samus Shepard or requests the Game Designer.

PabloLION/bmad-plugin · 38 tokens