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 danielrosehill/Claude-AI-Video-Producer-Plugin --skill script-to-ttsgit clone --depth 1 https://github.com/danielrosehill/Claude-AI-Video-Producer-PluginWrote 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/danielrosehill/claude-ai-video-producer-plugin/script-to-tts)<a href="https://agentmods.dev/skills/danielrosehill/claude-ai-video-producer-plugin/script-to-tts"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-ai-video-producer-plugin/script-to-tts/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/danielrosehill/claude-ai-video-producer-plugin/script-to-tts"><img src="https://agentmods.dev/badge/skills/danielrosehill/claude-ai-video-producer-plugin/script-to-tts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00123 | $0.00777 |
| Opus 5 | $0.00062 | $0.00388 |
| Sonnet 5 | $0.00025 | $0.00155 |
| Haiku 4.5 | $0.00012 | $0.00078 |
Grade A, and why
script-to-tts 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Script → TTS reformatter
You take a finished script and produce per-model, per-line TTS input files.
Inputs
scripts/final/script.md(or a draft path the user passes).- Target model — ask if not stated. Common:
elevenlabs,openai-tts,google-tts,azure-tts,hume,chatterbox. - Voice ID / preset, if known. Pull from
brief/tools-and-models.mdif listed.
Per-model behaviour
| Model | Format | Notable conventions |
|---|---|---|
| ElevenLabs | plain text + inline <break time="500ms"/> |
Keep chunks ≤ 5000 chars per request. Don't over-use breaks — the v3 models pace naturally. |
| OpenAI TTS | plain text | No SSML. Use punctuation for pacing. ≤ 4096 chars per request. |
| Google Cloud TTS | SSML | Full SSML supported: <break>, <emphasis>, <prosody rate="…" pitch="…">. |
| Azure (neural) | SSML with <voice> + mstts:express-as styles |
Style + degree work for some voices; check voice's supported styles. |
| Hume | plain text + emotional context note | Hume responds to expressed emotion in the prompt itself. |
| Chatterbox | plain text + reference voice | No SSML; rely on punctuation and the reference clip for prosody. |
Steps
- Read script. Identify VO segments (drop bracketed visual direction like
[wide shot of skyline]). - Split by beat — one file per numbered beat/scene so files map to storyboard shots.
- Normalise:
- Spell out unusual abbreviations (
API→ keep,e.g.→ "for example") if the model is known to mangle them. - Numbers: large/contextual numbers spelled out (
2026→ "twenty twenty-six" usually unnecessary for ElevenLabs but required for some Azure voices). - Quotes/dashes: convert smart quotes to straight, em-dashes to commas where pause is wanted.
- Spell out unusual abbreviations (
- Insert pacing markers per the model's supported syntax. Be conservative — a comma is usually enough.
- Save:
- SSML models:
scripts/tts/<model>/<NN>-<slug>.ssml - Plain models:
scripts/tts/<model>/<NN>-<slug>.txt
- SSML models:
- Emit a
scripts/tts/<model>/INDEX.mdlisting each file, character count, estimated duration (chars × ~14ms for typical speech rate), and the voice ID to use.
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 · 47 lines · 123 tokens per session scan A ab7414a449b2
script-to-tts is a skill published in the GitHub repository danielrosehill/Claude-AI-Video-Producer-Plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 123 tokens to every session and 777 once invoked, about $0.0006 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…