Menu
NEW AGENT
MY AGENTS
ASSISTANTS
Step 1:
Sample pack from YT video
1️⃣
Perfect output
- scan ALL
2️⃣ Add
output numbers
, then...
3️⃣ Add
Subagent Numbers
(work backwards
from output number!
)
4️⃣ Add
ACTUAL Skills
to subagent
✅ DONE..Copy x4 to Step 3...
SETTINGS
LOGOUT
What Shall We Build Next?
1
Describe
Describe your task
2
Refine
Refine the plan
3
SubAgents
Review all agents
4
Deploy
Deploy your agent
Sub Agent 1
Sub Agent 2
Sub Agent 3
Sub Agent 4
Sub Agent 5
Sub Agent 6
Sub Agent 7
Sub Agent 8
A) SUBAGENT SUMMARY: The YouTube Downloader subagent downloads the entire audio from a specified YouTube video as an MP3 file. B) FINAL TASK OUTPUT: A single MP3 file containing the entire audio from the specified YouTube video. The MP3 file will be saved on the internal server with a clear file name related to the video title. C) SUBAGENT INPUT: A valid YouTube video URL. E) SUBAGENT TASK SUMMARY: This subagent consists of a single skill: YouTube video URL input > #225 - Download Entire YouTube Video As MP3 > MP3 file output saved to internal server The YouTube video URL provided as input is passed to skill #225, which downloads the entire audio from the video as an MP3 file. The resulting MP3 file is then saved to the internal server, with the file name based on the video title for easy identification. F) SILOS: This subagent does not require any silos as it only involves a single skill. The MP3 file output from skill #225 is the final output of this subagent.
SubAgent #1 - Diagram
Expand Diagram
A) SUBAGENT SUMMARY: The Stem Separator subagent extracts the 3 best audio stems from 3 MP3 files. B) FINAL TASK OUTPUT: The final output of the Stem Separator subagent will be 9 MP3 files, consisting of the 3 best audio stems extracted from each of the 3 input MP3 files. The stems will be returned in order of volume/amplitude (loudest first), and only stems with a minimum level of loudness will be included. C) SUBAGENT INPUT: The subagent requires 3 MP3 files as its initial input to complete the tasks. E) SUBAGENT TASK SUMMARY: The Stem Separator subagent will use the following specific skills to extract the best audio stems from the input MP3 files: Input: 3 MP3 files > Skill #240 - Extract all audio stems (run 3 times, once for each MP3 file) > Skill #195 - Extract Beatpoints & Tempo of MP3 (run 9 times, once for each extracted stem) > Skill #196 - Create Visual Waveform Of Wav/mp3 File (run 9 times, once for each extracted stem) > Skill #198 - Analyze An Image With GPT Vision & Return Text (run 9 times to analyze the waveforms and determine stem volume/amplitude) > Skill #215 - Summarise and Return All Final Output Files (to return the final 9 best stems, 3 from each original MP3, ranked by volume) Output: 9 MP3 files (the 3 best stems from each of the 3 original MP3s, ranked by volume) F) SILOS: This subagent has 3 main silos that can run in parallel, one for processing each of the 3 input MP3 files: Silo 1: Input MP3 1 > Skill #240 > Skill #195 > Skill #196 > Skill #198 > Output top 3 stems from MP3 1 Silo 2: Input MP3 2 > Skill #240 > Skill #195 > Skill #196 > Skill #198 > Output top 3 stems from MP3 2 Silo 3: Input MP3 3 > Skill #240 > Skill #195 > Skill #196 > Skill #198 > Output top 3 stems from MP3 3 The outputs from the 3 silos are then combined: Silo 1 output + Silo 2 output + Silo 3 output > Skill #215 > Final output of top 9 stems total
SubAgent #2 - Diagram
Expand Diagram
A) SUBAGENT SUMMARY: The Tempo Analyzer subagent extracts tempo (BPM) and beat positions from three MP3 files. B) FINAL TASK OUTPUT: The final output of this subagent will be the tempo (BPM) and beat positions for each of the three input MP3 files. The output should be formatted as plain text, with the tempo listed as a number (e.g., "120 BPM") and the beat positions listed as timestamps (e.g., "0:00, 0:30, 1:00, 1:30"). C) SUBAGENT INPUT: The subagent requires three MP3 files as input, which should be provided by the Stem Separator subagent. The MP3 files should be stored on the internal server, and their URLs should be passed to the Tempo Analyzer subagent. E) SUBAGENT TASK SUMMARY: The Tempo Analyzer subagent will use the following skills to extract tempo and beat positions from the input MP3 files: 1. Receive 3 MP3 file URLs from the Stem Separator subagent 2. For each MP3 file URL: a. Call skill #195 - Extract Beatpoints & Tempo of MP3 - Input: MP3 file URL - Output: Tempo (BPM) and beat positions for the MP3 file b. Save the output as plain text 3. Combine the plain text outputs for all three MP3 files 4. Pass the combined plain text output to the next subagent (Sample Extractor) F) SILOS: This subagent does not require silos, as it performs the same task (extracting tempo and beat positions) for each of the three input MP3 files. The processing of each MP3 file can be done sequentially using a loop or iteration.
SubAgent #3 - Diagram
Expand Flow
A) SUBAGENT SUMMARY: The Sample Extractor subagent extracts audio samples of varying lengths from specific timestamps of MP3 files, utilizing tempo and beatpoint information. B) FINAL TASK OUTPUT: 24 audio samples in .wav format, consisting of 1, 2, 4, and 8 beat lengths extracted from 3 MP3 files at user-specified timestamps. The samples will be saved to the server with appropriate naming conventions indicating their source and characteristics. C) SUBAGENT INPUT: - 3 MP3 files from the Stem Separator subagent - Tempo (BPM) and beat positions for each MP3 file from the Tempo Analyzer subagent - 3 user-specified timestamps for each MP3 file E) SUBAGENT TASK SUMMARY: 1. Input: 3 MP3 files from Stem Separator, tempo and beat positions from Tempo Analyzer, and user-specified timestamps 2. For each MP3 file (repeated 3 times): a. Skill #224 - Extract & Download Section Of YouTube Video URL: Extract audio at the user-specified timestamp with a duration of 8 beats (based on tempo information) b. Skill #197 - Cut Wav/mp3 Audio into Multiple Pieces/Samples: Cut the extracted audio into samples of 1, 2, 4, and 8 beat lengths, starting from the user-specified timestamp c. Save the resulting samples to the server with appropriate naming conventions 3. Output: 24 audio samples (8 samples per MP3 file, consisting of 1, 2, 4, and 8 beat lengths) F) SILOS: Silo 1: Process MP3 file 1 - Input: MP3 file 1, tempo and beat positions, user-specified timestamp - Skill #224 - Extract & Download Section Of YouTube Video URL - Skill #197 - Cut Wav/mp3 Audio into Multiple Pieces/Samples - Save resulting samples to server - Output: 8 audio samples from MP3 file 1 Silo 2: Process MP3 file 2 - Input: MP3 file 2, tempo and beat positions, user-specified timestamp - Skill #224 - Extract & Download Section Of YouTube Video URL - Skill #197 - Cut Wav/mp3 Audio into Multiple Pieces/Samples - Save resulting samples to server - Output: 8 audio samples from MP3 file 2 Silo 3: Process MP3 file 3 - Input: MP3 file 3, tempo and beat positions, user-specified timestamp - Skill #224 - Extract & Download Section Of YouTube Video URL - Skill #197 - Cut Wav/mp3 Audio into Multiple Pieces/Samples - Save resulting samples to server - Output: 8 audio samples from MP3 file 3
4 Template & Links
Expand Flow
A) SUBAGENT SUMMARY: The Sample Curator subagent generates waveforms for audio samples, analyzes them to select the top samples based on volume, and outputs a ranked list of the best samples. B) FINAL TASK OUTPUT: A ranked list of the top 12 audio samples (out of 24 total samples) based on volume criteria, saved as a text file. C) SUBAGENT INPUT: - 24 audio sample files in WAV or MP3 format - Tempo and beat position information for each audio file D) SUBAGENT TASK SUMMARY: 1. Input: 24 audio sample files 2. For each audio file (repeat 24 times): - Skill #196 - Create Visual Waveform Of Each Wav/mp3 File - Save the waveform image file 3. For each waveform image (repeat 24 times): - Skill #198 - Analyze An Image With GPT Vision & Return Text - Prompt: "Analyze the waveform image and return the average volume level of the audio on a scale of 1-10." - Save the volume score for each sample 4. Sort the 24 samples by their volume scores in descending order 5. Select the top 12 samples from the sorted list 6. Save the list of top 12 sample filenames and their volume scores as a text file 7. Output: Text file with ranked list of top 12 audio samples E) SILOS: Silo 1: Generate waveform images - Input: 24 audio sample files - Skill #196 repeated 24 times - Output: 24 waveform image files Silo 2: Analyze waveform images - Input: 24 waveform image files - Skill #198 repeated 24 times - Output: Volume scores for 24 samples Silo 3: Rank and select top samples - Input: Volume scores for 24 samples - Sort samples by volume score - Select top 12 samples - Output: Text file with ranked list of top 12 samples
5 Template & Links
Expand Flow
A) SUBAGENT SUMMARY: The Zip Creator subagent compresses the 12 selected and organized audio samples into a single zip file for easy distribution. B) FINAL TASK OUTPUT: A single compressed zip file containing 12 audio samples in .wav format, organized using a naming convention that reflects each sample's source timestamp, stem type (instrumental or vocal), and beat length. C) SUBAGENT INPUT: - Directory containing 12 selected and organized audio samples from the Sample Curator subagent E) SUBAGENT TASK SUMMARY: 1. Receive the directory containing 12 selected and organized audio samples from the Sample Curator subagent 2. skill/action1: #175 - Zip Internal URLs - Input: Directory containing 12 selected and organized samples - Output: Compressed zip file 3. Return the URL of the compressed zip file, with both internal and external links, along with an explanation of what was zipped F) SILOS: This subagent does not require any silos as it consists of a single action step.
6 Template & Links
Expand Flow
Templates & Links Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry's standard dummy text ever since the 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book. It has survived not only five centuries, but also the leap into electronic typesetting, remaining essentially unchanged. It was popularised in the 1960s with the release of Letraset sheets containing Lorem Ipsum passages, and more recently with desktop publishing software like Aldus PageMaker including versions of Lorem Ipsum.
7 Template & Links
Expand Flow
Questions & Research Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry's standard dummy text ever since the 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book. It has survived not only five centuries, but also the leap into electronic typesetting, remaining essentially unchanged. It was popularised in the 1960s with the release of Letraset sheets containing Lorem Ipsum passages, and more recently with desktop publishing software like Aldus PageMaker including versions of Lorem Ipsum.
8 Template & Links
Expand Flow
Templates & Links Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry's standard dummy text ever since the 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book. It has survived not only five centuries, but also the leap into electronic typesetting, remaining essentially unchanged. It was popularised in the 1960s with the release of Letraset sheets containing Lorem Ipsum passages, and more recently with desktop publishing software like Aldus PageMaker including versions of Lorem Ipsum.
9 Template & Links
Expand Flow
Templates & Links Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry's standard dummy text ever since the 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book. It has survived not only five centuries, but also the leap into electronic typesetting, remaining essentially unchanged. It was popularised in the 1960s with the release of Letraset sheets containing Lorem Ipsum passages, and more recently with desktop publishing software like Aldus PageMaker including versions of Lorem Ipsum.
10 Template & Links
Expand Flow
Questions & Research Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry's standard dummy text ever since the 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book. It has survived not only five centuries, but also the leap into electronic typesetting, remaining essentially unchanged. It was popularised in the 1960s with the release of Letraset sheets containing Lorem Ipsum passages, and more recently with desktop publishing software like Aldus PageMaker including versions of Lorem Ipsum.
11 Template & Links
Expand Flow
Templates & Links Lorem Ipsum is simply dummy text of the printing and typesetting industry. Lorem Ipsum has been the industry's standard dummy text ever since the 1500s, when an unknown printer took a galley of type and scrambled it to make a type specimen book. It has survived not only five centuries, but also the leap into electronic typesetting, remaining essentially unchanged. It was popularised in the 1960s with the release of Letraset sheets containing Lorem Ipsum passages, and more recently with desktop publishing software like Aldus PageMaker including versions of Lorem Ipsum.
12 Template & Links
Expand Flow
Need To Start Afresh?
BACK TO REFINE
Tweaked & Good To Go?
PROCEED TO DEPLOY
