YouTube Audio Samples Extractor

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. Finally we will want to save all the files to a server and present the download links.

First, pre-entered info...

final-output2

The final output of this automated workflow would be a zip file containing a collection of music samples in .wav format. These samples would be extracted from a specified YouTube video at three different time points (e.g., 5 seconds, 130 seconds, 190 seconds). For each time point, the audio would be separated into instrumental and vocal stems, resulting in a total of 6 separate audio files. From each of these audio files, samples of varying lengths (1, 2, 4, or 8 beats) would be extracted based on the tempo and beat positions. The total number of samples generated might be filtered down to the best 48 samples (or a user-specified number) based on certain criteria like average amplitude. All these final sample files would be saved on a server and compressed into a single zip file for easy distribution and download.

subagents-extracted2

OVERVIEW OF SUBAGENTS: SUBAGENT 1: YouTube Downloader - Skill: #225 - Download Entire YouTube Video As MP3 - Description: Inputs a YouTube video URL, and returns an MP3 file - Input Needed: YouTube URL - Output: MP3 URL SUBAGENT FINAL OUTPUT: [youtube-audio-mp3] SUBAGENT 2: Audio Splitter - Skill: #240 - Extract all audio stems - Description: This skill will input an MP3 URL and extract all instruments and variations, then return between 1-10x MP3s. MP3s will be returned in order of volume/amplitude (ie most loudest first), and only stems with a minimum level of loudness will be returned (so if an MP3 has no woodwind instruments, then that audio will not be included). Stems that can be extracted include: Vocals, instrumental, drums, bass guitar, electric guitar, acoustic guitar, piano, synthesizer, strings, wind - Input: MP3 URL - Output: 1-10x MP3 URLs (arranged in order of importance) SUBAGENT FINAL OUTPUT: [audio-stems] SUBAGENT 3: Beat Analyzer - Skill: #195 - Extract Beatpoints & Tempo of MP3 - Description: This skill will extract beatpoints, downbeats and tempo (BPM) from any MP3 file. - Input Needed: mp3 URL - Output: a nice clean breakdown of beatpoints and downbeats for the sample SUBAGENT FINAL OUTPUT: [beat-tempo-info] SUBAGENT 4: Sample Extractor - Skill: #197 - Cut Wav/mp3 Audio into Multiple Pieces/Samples - Description: This skill takes a wav or mp3 file, along with start/end time of audio to be extracted and returns the extracted files as a list of new wav URLs - Input Needed: wav URL and timings to cut (start/end time per required file to be cut) - Output: a list of all URLs of wav files (based on volume from waveform, intro, close, etc.. mix of 2/4/8 beat samples.. nice list) SUBAGENT FINAL OUTPUT: [extracted-samples] SUBAGENT 5: Output Organizer - Skills Used: #215 - Summarise and Return All Final Output Files DESCRIPTION: This skill returns a summary of various previous skills that have completed, and is particularly useful when appearing at the end of an entire Agent task, silo or sequence of skills. INPUT NEEDED: at least one output (perhaps other supplementary ones that may be helpful) OUTPUT: nice text summary containing 1 or more outputs - Accomplishment: Organize the selected sample files, rename them according to the naming convention, compress them into a zip file, and generate a summary of the final output. SUBAGENT FINAL OUTPUT: [final-sample-pack] SEQUENCE OF SUBAGENTS: 1. YouTube Downloader: Download the MP3 from the YouTube video 2. Audio Splitter: Extract instrumental and vocal stems from the MP3 3. Beat Analyzer: Detect the tempo and beat positions of the original audio 4. Sample Extractor: Chop the stems into samples based on tempo, beat positions, and user-specified timestamps 5. Output Organizer: Provide download links along with a summary of the final output

subagentnumber

[subagentnumber]

Then, agent response...

subagent1refined-new-json-core

G) TASKFLOW SUMMARY - ID: #225 - Title task: Download Entire YouTube Video As MP3 - Description of the task: This skill takes a YouTube video URL as input and downloads the entire audio from the video, saving it as an MP3 file on the server. It returns the internal and external URLs of the saved MP3 file. - Input(s) involved: YouTube video URL - Output token name: [youtube-audio-mp3]

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[YouTube Video URL] --> B{#225 - Download Entire YouTube Video As MP3} B --> C[MP3 file saved on server] C --> D[Return internal and external URLs of MP3 file] D --> E[youtube-audio-mp3] </div> <script> mermaid.initialize({ startOnLoad: true }); </script> </body> </html>

Mermaid Image - https://static.aiz.ac/1720627901-mermaid/mermaid1.png

prompts-required

[prompts-required]

subagent1-json-array

[ { "taskID": 1, "semanticTitleOfTask": "Download YouTube Video As MP3", "taskDescription": "This task takes a YouTube video URL as input and downloads the entire audio from the video, saving it as an MP3 file on the server.", "inputDescription": "The URL of the YouTube video to download the audio from.", "inputRequired": ["youtube-video-url"], "outputDescription": "The MP3 file containing the full audio from the specified YouTube video, saved on the server with both an internal and external URL provided.", "outputName": "youtube-audio-mp3", "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[Input: YouTube Video URL] -->|youtube-video-url| B{Download YouTube Video As MP3} B -->|youtube-audio-mp3| C[Output: MP3 File with Internal and External URLs] </div> <script> mermaid.initialize({ startOnLoad: true }); </script> </body> </html>