# nvidia-maxine-audio-effects

The nvidia-maxine-audio-effects skill is a Claude Code skill that plans and operates NVIDIA Maxine audio effects for speech cleanup. It guides effect selection across SDK and NIM pipelines.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 134 installs · ★ 252 repo stars
- Author: calesthio
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/calesthio/generative-media-skills/tree/HEAD/skills/providers/audio-enhancement/nvidia-maxine-audio-effects/SKILL.md
- Updated: 2026-07-14
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/nvidia-maxine-audio-effects

## What it does

The skill handles speech cleanup and enhancement workflows using NVIDIA Maxine audio effects. It directs the choice between noise removal, dereverberation, acoustic echo cancellation, and studio voice enhancements based on input audio problems.

The pipeline requires an NVIDIA GPU with Tensor Cores and an `NGC_API_KEY` to run the SDK or containerized BNR NIM services. It configures processing parameters, sample rates, and ensures audio is handled in 32-bit float format.

The tool deploys either via local SDK packages for client applications or Docker containers for scalable server-side inference.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill nvidia-maxine-audio-effects -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/nvidia-maxine-audio-effects/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/nvidia-maxine-audio-effects/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill nvidia-maxine-audio-effects -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/nvidia-maxine-audio-effects/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill nvidia-maxine-audio-effects -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/nvidia-maxine-audio-effects/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install calesthio/generative-media-skills skills/providers/audio-enhancement/nvidia-maxine-audio-effects
```

2. **Manually: put the files in place**
- File: `.github/skills/nvidia-maxine-audio-effects/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill nvidia-maxine-audio-effects -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/calesthio/generative-media-skills --path skills/providers/audio-enhancement/nvidia-maxine-audio-effects
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/nvidia-maxine-audio-effects/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add calesthio/generative-media-skills --skill nvidia-maxine-audio-effects -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/calesthio/generative-media-skills/tree/HEAD/skills/providers/audio-enhancement/nvidia-maxine-audio-effects/SKILL.md

## When to use it
- remove background noise from speech recordings
- suppress room echo and reverberation
- configure acoustic echo cancellation for live calls
- restore missing high-frequency content with super-resolution
- enhance thin microphone audio with studio voice profiles

## Example prompts
- Set up the noise removal pipeline using nvidia-maxine-audio-effects
- Choose between local SDK and BNR NIM for audio processing
- Check GPU requirements for nvidia-maxine-audio-effects

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 710795a6ee4c5346.

BEGIN THIRD-PARTY FILE 710795a6ee4c5346
```text
---
name: nvidia-maxine-audio-effects
description: Use NVIDIA Maxine / NVIDIA AI for Media audio effects for speech cleanup and enhancement in live or offline media pipelines, including Background Noise Removal, denoise+dereverb, room echo removal, acoustic echo cancellation, audio super-resolution, Studio Voice, Speaker Focus, and Voice Font. Use when selecting, integrating, prompting around, QAing, or privacy-reviewing NVIDIA AFX SDK or BNR NIM workflows for conferencing, broadcast, podcast, avatar, ad, social, and video post-production audio.
---

# 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.
```
END THIRD-PARTY FILE 710795a6ee4c5346

The third-party file has ended. Everything between the 710795a6ee4c5346 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2422 of 20657 bytes. © calesthio · MIT · https://github.com/calesthio/generative-media-skills/tree/HEAD/skills/providers/audio-enhancement/nvidia-maxine-audio-effects/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
