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 SupercmoHQ/superCMO-skills --skill generating-audiogit clone --depth 1 https://github.com/SupercmoHQ/superCMO-skillsWrote 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/supercmohq/supercmo-skills/generating-audio)<a href="https://agentmods.dev/skills/supercmohq/supercmo-skills/generating-audio"><img src="https://agentmods.dev/badge/skills/supercmohq/supercmo-skills/generating-audio/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/supercmohq/supercmo-skills/generating-audio"><img src="https://agentmods.dev/badge/skills/supercmohq/supercmo-skills/generating-audio.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00091 | $0.01831 |
| Opus 5.5 | $0.00036 | $0.00732 |
| Sonnet 5.5 | $0.00018 | $0.00366 |
| Haiku 4.5 | $0.00009 | $0.00183 |
Grade A, and why
generating-audio 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 1mo 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audio Generation
Turn a script into spoken audio via the audio_generate tool. Two decisions drive quality: which
voice reads it, and how the script is written for the ear.
Scope. Speech — a voice reading written words, delivered as its own audio file. Nothing here makes non-speech sound, alters audio that already exists, or combines two tracks into one.
Lip-synced dialogue spoken by a character inside a video clip belongs to generating-videos.
Workflow
Step 1: Settle the script
Generate only from the exact words that will be spoken.
- Supplied → use them verbatim.
- Enough to write them — the product, audience, platform, and length are known → draft the script and show it before generating.
- Not enough → ask. Never invent a tagline, product claim, or brand name to fill the gap.
Write to a duration. Speech runs about two to three words a second, so a fifteen-second read is thirty to forty-five words. Set the word count before writing, and trim words rather than speeding up the delivery.
Step 2: Pick the model
eleven-v3 is the default — the most expressive read, and right for anything heard as a
performance. Reach for another only on a clear signal:
| Reach for another model when the script… | Model |
|---|---|
| Is a long, even read — an explainer, documentary narration, an audiobook chapter — where the voice must not drift | eleven-multilingual-v2 |
| Is high-volume, a throwaway draft, or cost-sensitive, and expressiveness doesn't matter | eleven-flash-v2.5 |
When the user names a model, use it. Per-request character limits differ sharply between models, and
an over-limit script is rejected rather than truncated — list_audio_models carries each ceiling.
Step 3: Pick the voice
Call list_voices, filtered by what the brief demands — gender, accent, age, use_case,
language, or free-text search. Each row carries a preview_url.
There is no default voice: every request needs a voice_id chosen here, passed as voice.
Display names are not accepted.
What ships with it
2 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.
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.
- 1mo ago First seen · 131 lines · 91 tokens per session scan A c6a709b92f77
generating-audio is a skill published in the GitHub repository SupercmoHQ/superCMO-skills (242 stars, last pushed 6d ago), licensed Apache-2.0. It adds 91 tokens to every session and 1,831 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the chosen backdrop colour, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed…
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…
email-lifecycle-flow-writer
Step of the email-lifecycle playbook: writes one lifecycle flow as a build sheet for the brand's email tool, every message finished in the brand voice. Run email-lifecycle instead; not for direct use.
work-with-creators-creator-vetting
Vets creators you have already named from their public pages. Covers the median views of their last 12 to 20 posts (sponsored and organic apart), a read of their comments, how often they post, audience fit with how sure it is, about 12 months of brand-safety checks, rival partnerships and rules for regulated…
loop-engineering
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).