Download

Skill UI

Browse and discover 6557+ curated skills

All Development Artificial Intelligence Design & Creative Product & Business Data Science Marketing Soft Skills Productivity Engineering Languages

Search Audio , found 60 results

Default Newest Most Downloaded

Document Markdown Converter

K-Dense-AI/claude-scientific-skills

MarkItDown converts PDFs, Office docs, images, audio, HTML, CSV/JSON/XML, archives, and YouTube content into clean Markdown so LLMs can consume structured, token-efficient source material via CLI or Python APIs including OCR, transcription, and AI image captions.

Self-Hosted Research Notebook

K-Dense-AI/claude-scientific-skills

Open Notebook is a self-hosted, open-source alternative to NotebookLM that ingests PDFs, videos, audio, and webpages into notebooks, offers a REST API, multi-provider AI, context-aware chat, vector search, and podcast generation for privacy-first research workflows.

Hugging Face Transformers

K-Dense-AI/claude-scientific-skills

Load Hugging Face Transformers to run pipelines for text, vision, audio, and multimodal inference, customize model loading, tokenize inputs, and fine-tune with distributed training on domain-specific datasets.

Seedance Cinema Director

muapi-seedance-2

SamurAIGPT/Generative-Media-Skills

Transform briefs into cinematic videos via Seedance 2.0, guiding text/image/video/audio inputs through director-level directives, multimodal tagging, and synchronized sound for 4-15s outputs.

Real-Time Multimodal Pipeline

sickn33/antigravity-awesome-skills

Documentation for the Pipecat-powered Daily framework that guides agents through building production-ready real-time voice and multimodal AI pipelines, covering low-latency audio/video/text flows, transport choices, LLM/tool orchestration, and turn/context management.

EarLLM Android Build

sickn33/antigravity-awesome-skills

Build, maintain, and extend the EarLLM One Kotlin/Compose Android app that routes Bluetooth earbud voice through STT → LLM → TTS, handles SCO/BLE audio, permissions, and device quirks, and keeps stateflow-driven UIs and services in sync.

VideoDB Media Operator

affaan-m/everything-claude-code

VideoDB Media Operator hooks into local files, URLs, RTSP streams, and desktop capture to extract context, index visual/audio cues, transcode assets, edit timelines, build searchable clips, and drive alerts or generated media.

Fal AI Media Studio

affaan-m/everything-claude-code

Fal.ai Media Studio via MCP unifies image, video, and audio generation using Nano Banana, Seedance, Kling, Veo 3, CSM-1B, and ThinkSound models, enabling prompt-driven drafts, high-fidelity renders, and multimodal content for creative workflows.

Steganography Detection Workflow

performing-steganography-detection

mukul975/Anthropic-Cybersecurity-Skills

Guide for detecting and extracting hidden data embedded in images, audio, and video using metadata inspection, automated steganalysis tools, brute-force extraction, and LSB analysis to uncover covert channels during incident response and forensics.

Detect Deepfake Vishing Audio

detecting-deepfake-audio-in-vishing-attacks

mukul975/Anthropic-Cybersecurity-Skills

Detects AI-generated deepfake audio in vishing attacks by extracting spectral features (MFCC, centroid, contrast, ZCR) and scoring batches of samples to support SOC, incident response, and forensic analysis.

Remotion Video Creation Guide

remotion-video-creation

affaan-m/everything-claude-code

Collection of best practices for Remotion video creation in React, covering 3D, animations, audio, captions, charts, transitions, Tailwind, and more to guide domain-specific composition work.

Conversational Podcast Generator

podcast-generation

bytedance/deer-flow

Transforms user articles, reports, or documentation into natural two-host conversational podcasts by building structured JSON scripts and running the bundled TTS pipeline to emit MP3 audio plus transcripts.

Language