AI Skills for FFmpeg

Streamlines video editing workflows using AI for efficient cutting, structuring, and enhancing of real footage.

Automates audio-to-text transcription, generating professional Markdown documentation and summaries for meetings and lectures.

Converts voice notes and melodic recordings into quantized MIDI files using machine learning for pitch detection and intelligent processing.

Analyzes video ads using Gemini Vision AI for frame extraction, OCR, audio transcription, and scene analysis.

Analyzes Loom recordings to create structured, automatable workflows, enhancing business process understanding and efficiency.

Facilitates advanced video and audio processing tasks using FFmpeg for transcoding, filtering, and metadata manipulation.

Generates and stitches short videos using Google Veo 3.x and the Gemini API for ads and product demos with a reproducible CLI workflow.

Transforms YouTube videos into a comprehensive content suite, including blog posts, social media threads, and video clips.

Enables offline text-to-speech responses using local Piper voices, perfect for generating voice replies in multiple languages.

Generates and stitches short videos using Google Veo 3.x and the Gemini API for ads and product demos with a CLI workflow.

Creates narrated videos from Excalidraw diagrams using TTS and Remotion, ideal for engaging explainer content.

Generates lip-sync videos by combining an image with a user's audio recording, preserving exact audio timing for personalized content.

Analyzes YouTube videos by synchronizing audio transcripts with visual frames for detailed step-by-step guides.

Converts voice messages to text using Yandex SpeechKit, enabling seamless audio transcription in OpenClaw-connected applications.

Analyzes ad videos to generate detailed markdown reports, frameworks, and storyboards for improved performance in advertising.

Transcribes Chinese audio files to text using Zhipu AI's GLM-ASR model, enhancing accuracy with context prompts and custom hotwords.

Generates AI-powered short videos from topics or reference videos, perfect for social media and e-commerce content creation.

Analyzes video content by extracting frames at regular intervals, aiding in scene understanding and content review.

Transcribes audio to text with ElevenLabs Scribe, supporting batch and real-time transcription for various audio formats.

Enables real-time voice conversations in Discord using Claude AI for transcription and text-to-speech capabilities.