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 calesthio/generative-media-skills --skill nvidia-maxine-audio-effectsgit clone --depth 1 https://github.com/calesthio/generative-media-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/calesthio/generative-media-skills/nvidia-maxine-audio-effects)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/nvidia-maxine-audio-effects"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/nvidia-maxine-audio-effects/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/calesthio/generative-media-skills/nvidia-maxine-audio-effects"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/nvidia-maxine-audio-effects.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 | $0.00109 | $0.04312 |
| Opus 5 | $0.00055 | $0.02156 |
| Sonnet 5 | $0.00022 | $0.00862 |
| Haiku 4.5 | $0.00011 | $0.00431 |
Grade A, and why
nvidia-maxine-audio-effects 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 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.
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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NVIDIA Maxine audio effects
Use this skill to plan and operate NVIDIA Maxine Audio Effects, now under NVIDIA AI for Media, as an audio cleanup and enhancement stage. Treat it as a production and integration skill, not as a sound-generation prompt recipe: the core work is choosing the correct effect, preparing audio correctly, protecting speaker rights, running the SDK or NIM in the right runtime, and proving that the processed speech is clearer without damaging the performance.
Facts below were verified against official NVIDIA documentation on 2026-07-10. Re-check NVIDIA docs, NGC, and license terms before quoting exact model profiles, supported GPUs, SDK versions, file limits, or access requirements in a production proposal.
Capability boundaries
NVIDIA documents these Audio Effects SDK capabilities:
denoiser/ Background Noise Removal (BNR): remove common background noises from speech while preserving natural speech as much as possible.dereverb: suppress room echo/reverberation from recordings made in reflective rooms.dereverb_denoiser: use the combined denoise + dereverb model when both noise and reverb are present; do not chain separate denoiser and dereverb effects when NVIDIA provides the combined effect for that case.aec: acoustic echo cancellation for live bidirectional communication. This is not the same as dereverb; it needs near-end microphone audio plus a far-end/reference signal.superres: audio super-resolution, typically 8 kHz -> 16 kHz or 16 kHz -> 48 kHz, to restore/predict missing high-frequency content.studio_voice_high_quality: offline enhancement for degraded speech from poor microphones, noise filters, beamforming, static, or non-ideal acoustics.studio_voice_low_latency: real-time Studio Voice variant; use for live conferences or broadcasts, not offline batch finishing.speaker_focus: Early Access speaker isolation for keeping the primary speaker while suppressing other speakers and some noises.voice_font_high_quality/voice_font_low_latency: Early Access any-to-any voice conversion using reference speech. Treat as voice identity transformation requiring explicit consent and review.
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.
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.
- 9d ago First seen · 275 lines · 109 tokens per session scan A 8b7eda1e53f8
nvidia-maxine-audio-effects is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 109 tokens to every session and 4,312 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
cliptalk-cover-director
Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.
cliptalk-smart-reframe
Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.
cliptalk-content-extractor
Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.
cliptalk-interview-editor
Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.
cliptalk-shortform-hook-director
Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.
cliptalk-social-reframe-exporter
Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…