YouTube Audio Sample Generator

I want to input a youtube video, then get a collection of music samples returned to me (.wav files in a zip). I think I should specify 3 specific times (eg 5 seconds, 130 seconds, 190 seconds, and then the agent rip the audio file from YouTube, then extract stems (instrumentals, vocals), and then extract (say) 16 beats worth of audio - beginning from the 3 timings I've entered. This gives us 3x separate audio sections to sample, and if we then separate them into vocals and instrumentals that then gives us 6x separate audio files to sample from (although we will use the initial tempo/beatpoint for all 6). Next we will want to use the beatpoint and tempo to extract samples (eg 1/2/4/8 beat in lengths, beginning from the beatpoints). So we chopup the samples eg using SOX, perhaps chopping based on beat length (if BPM = 90bpm, then 1 beat is 0.66secs) and beat position, and chopping maybe a mix of 1/2/4/8 beat samples. This will likely give us far too many samples, so we may want to finally filter them down (to "the best 48 samples"). We could do this by using a library like Librosa to filter somehow (eg based on average amplitude), and rank the samples. We will likely need to calculate how many samples we are going to get, how/if to rank them, and then generate them acccordingly. I am not sure whether we should filter or just do a bulk import. Finally we will want to save all the files to a server and zip them up

First, pre-entered info...

final-output2

A zip file containing approximately 24-48 .wav audio files, organized in a structured folder hierarchy. These files will be: - Short, beat-aligned audio samples of varying lengths (1, 2, 4, or 8 beats) - Derived from both vocal and instrumental stems - Named systematically (e.g., "130sec_vocal_4beat_1.wav") - High-quality audio format (44.1kHz, 16-bit)

subagents-extracted2

OVERVIEW OF AGENTS: Purpose: Download and process YouTube audio via a series of specialized agents that handle different aspects of audio processing and sample pack creation. Each agent performs specific tasks using a combination of existing and required skills. SUBAGENT 1: MEDIAAGENT - Purpose: Download and process YouTube audio - Final Output: [raw-wav-audio] - Skills: - #193 Download Entire YouTube Video As MP3 - #178 Convert 1-20 MP3s to wav - Sequence: Download YouTube video > Convert to MP3 > Convert to WAV SUBAGENT 2: ANALYSISAGENT - Purpose: Detect tempo and extract stems - Final Output: [analyzed-stem-sections] - Skills: - #180 Extract Beatpoints & Tempo of MP3 - #197 Extract Instrumental & Vocal From MP3 - #178 Convert MP3 stems to WAV - Sequence: Analyze tempo > Extract stems > Convert to WAV format SUBAGENT 3: SAMPLEAGENT x2 (for both instrumental and vocal) - Purpose: Generate and analyze beat-aligned samples - Final Output: [vocal-beat-samples] and [instrmental-beat-samples] - Skills: - #219 Cut Wav/mp3 Audio into Multiple Pieces/Samples - Repeat for both vocal and instrumental WAV - Sequence: Cut audio SUBAGENT 4: PACKAGEAGENT - Purpose: Organize and deliver final samples - Final Output: [final-sample-pack] - Skills: - File Organization Function - Generate metadata.json - Create zip archive - Sequence: Generate metadata > Create archive

subagentnumber

[subagentnumber]

Then, agent response...

subagent1refined-new-json-core

G) TASKFLOW SUMMARY Based on the MEDIAAGENT subagent workflow, here are the two core skills/tasks identified: 1. - ID: #193 - Title task: Download Entire YouTube Video As MP3 - Description: Downloads a YouTube video and extracts its audio content into MP3 format, ensuring high-quality audio preservation and proper metadata handling - Input(s) involved: [youtube-url], [desired-filename] - Output token name: [downloaded-mp3] 2. - ID: #178 - Title task: Convert MP3 to WAV Format - Description: Converts MP3 audio file to high-quality WAV format (44.1kHz, 16-bit), maintaining audio fidelity and preparing for subsequent audio processing tasks - Input(s) involved: [downloaded-mp3], [desired-wav-filename] - Output token name: [raw-wav-audio] Additional Processing Tasks (these are internal processes, not numbered skills): 3. - ID: (internal process) - Title task: URL Validation and Filename Generation - Description: Validates YouTube URL format and generates standardized filename for consistent processing - Input(s) involved: [youtube-url] - Output token name: [validated-url], [standardized-filename] 4. - ID: (internal process) - Title task: Error Handling and Quality Verification - Description: Monitors download and conversion processes, handles errors, and verifies output audio quality meets specifications - Input(s) involved: [downloaded-mp3], [raw-wav-audio] - Output token name: [verification-status] The complete flow follows this sequence: [youtube-url] → [validated-url] → [downloaded-mp3] → [raw-wav-audio] → [verification-status]

subagent1mermaid

<!DOCTYPE html> <html> <head> <title>Mermaid Diagram Example</title> <script src="https://cdnjs.cloudflare.com/ajax/libs/mermaid/9.4.3/mermaid.min.js"></script> </head> <body> <div class="mermaid"> graph TD A[Input: YouTube URL] -->|Validation| B[URL Validation Process] B -->|Valid URL| C[Generate Standard Filename] B -->|Invalid URL| H[Error: Invalid URL] C --> D[Download YouTube as MP3] D -->|Success| E[Convert MP3 to WAV] D -->|Failure| I[Error: Download Failed] E -->|Success| F[Quality Verification] E -->|Failure| J[Error: Conversion Failed] F -->|Passes| G[Output: Raw WAV Audio] F -->|Fails| K[Error: Quality Check Failed] G --> L[Save to Server] L -->|Success| M[Final Output: source_full_audio.wav] L -->|Failure| N[Error: Save Failed] </div> <script> mermaid.initialize({ startOnLoad: true }); </script> </body> </html>

Mermaid Image - https://static.aiz.ac/1734510151-mermaid/mermaid1.png

prompts-required

[prompts-required]

subagent1-json-array

[ { "taskID": 1, "semanticTitleOfTask": "URL Validation and Filename Generation", "taskDescription": "Validates YouTube URL format and generates a standardized filename following our convention (timestamp + cleaned video title)", "inputDescription": "YouTube URL string that needs to be validated and processed for filename generation", "inputRequired": ["youtube-url"], "outputDescription": "Two outputs: 1) A validated YouTube URL confirmed to match standard format, 2) A standardized filename following our naming convention", "outputName": ["validated-url", "standardized-filename"], "promptInstruction": "Given a YouTube URL, validate its format (must be youtube.com/watch?v= or youtu.be/) and generate a filename with format: YYYYMMDD_HHMMSS_cleaned_video_title_source_full.wav" }, { "taskID": 193, "semanticTitleOfTask": "YouTube Video Audio Extraction", "taskDescription": "Downloads YouTube video and extracts high-quality MP3 audio, preserving audio fidelity and metadata", "inputDescription": "Validated YouTube URL and standardized filename to save the downloaded MP3", "inputRequired": ["validated-url", "standardized-filename"], "outputDescription": "MP3 file containing the full audio from the YouTube video, saved with our standardized filename", "outputName": "downloaded-mp3", "promptInstruction": "" }, { "taskID": 178, "semanticTitleOfTask": "MP3 to WAV Conversion", "taskDescription": "Converts the downloaded MP3 to a high-quality WAV format (44.1kHz, 16-bit) for subsequent processing", "inputDescription": "MP3 file URL from previous download task", "inputRequired": ["downloaded-mp3"], "outputDescription": "High-quality WAV file (44.1kHz, 16-bit) ready for further audio processing", "outputName": "raw-wav-audio", "promptInstruction": "" }, { "taskID": 4, "semanticTitleOfTask": "Audio Quality Verification", "taskDescription": "Verifies the WAV file meets our quality specifications and handles any conversion errors", "inputDescription": "WAV file generated from the conversion process", "inputRequired": ["raw-wav-audio"], "outputDescription": "Verification status confirming audio quality meets specifications (44.1kHz, 16-bit) and file integrity", "outputName": "verification-status", "promptInstruction": "" } ]

subagent1-json-array-mermaid

<!DOCTYPE html> <html> <head> <title>Mermaid Diagram Example</title> <script src="https://cdnjs.cloudflare.com/ajax/libs/mermaid/9.4.3/mermaid.min.js"></script> </head> <body> <div class="mermaid"> graph TD A[YouTube URL Input] -->|Input| B[Task 1: URL Validation] B -->|validated-url| C[Task 193: Download Audio] B -->|standardized-filename| C C -->|downloaded-mp3| D[Task 178: Convert to WAV] D -->|raw-wav-audio| E[Task 4: Quality Verification] E -->|verification-status| F[Final Output: WAV File] subgraph MEDIAAGENT Flow B C D E end style A fill:#f9f,stroke:#333,stroke-width:2px style F fill:#9f9,stroke:#333,stroke-width:2px </div> <script> mermaid.initialize({ startOnLoad: true }); </script> </body> </html>