Internal Build Plan · Confidential

Affirmology Demo Build Plan

From zero to a working 5 to 10 minute personalized audio in 3 to 4 focused days

Overview

The goal and the constraint.

Goal: produce one working audio track based on Jeff's own birth data and Gene Keys sequence. The track should be magical enough to make someone who listens to it on a phone go "holy shit, this was made for me." This single audio becomes the proof point for Sunday with Josh, Thursday with Colin, and Omaha conversations.

Constraint: manual build, no agent automation yet. This is a one-off proof of concept using ElevenLabs and Suno directly. The agent architecture comes later. Right now, you are the agent.

Timeline: 3 to 4 days of focused work, ideally 4 to 6 hours per day. Doable between now and Sunday if you start tomorrow.

Why this is the right move: a working 5-minute audio is worth more than ten executive summaries in any investor conversation. "Here, listen to this" beats "here, read this" every single time.
Tools Needed

The full stack for this manual demo.

Total monthly cost if you sign up for everything fresh: $52 plus the Claude Pro you already have. Cancellable after the demo if you want to pause subscriptions until the funded build phase.

Day 1 · Data & Script

Get the foundation in place.

Day 1, Morning · 2 hours

Step 1: Gather your data into the Affirmology folder

Create a new file called jeff_chart_data.md in the AFFIRMOLOGY folder. Include:

  • Birth date, time, and city
  • Your Gene Keys profile: Life's Work, Evolution, Radiance, Purpose, Vocation, Culture, Brand, Pearl, IQ, EQ, SQ, Attraction, Style. Each as the Gene Key number + line.
  • Your astrology: Sun, Moon, Rising. Major planet placements (Mars, Venus, Mercury, Jupiter, Saturn) by sign and house.
  • Your Human Design type, profile, authority, defined and undefined centers.
  • Optional: current transit notes (which planets are in which signs right now, any upcoming significant transits like Mercury retrograde, new moon, full moon).

You said you have most of this somewhere already. Just consolidate it into one file so Claude can ingest it cleanly.

Day 1, Afternoon · 3 hours

Step 2: Generate the affirmation script with Claude

Open a fresh Claude conversation. Paste the data file. Then use this prompt:

Master Prompt for Script Generation You are an expert affirmation writer with deep knowledge of Gene Keys, Human Design, and astrology. I am building a personalized 7 to 10 minute audio for myself using ElevenLabs voice and Suno music. Use my chart data attached.

Generate a complete spoken-word script for the audio. Structure it in four parts:

PART 1 (1 minute): Heart coherence induction. Slow guided breathing instruction. 5-second inhale, 5-second exhale. Direct the listener (me) to feel into the heart center. Brief and warm.

PART 2 (2 minutes): I AM affirmations rooted in my Gene Keys gift-level energy. Use the gift descriptions of my Life's Work, Evolution, and Radiance Gene Keys specifically. Frame each as "I am..." and repeat key phrases for hypnotic effect (Abraham-Hicks remix style). 8 to 12 affirmations total.

PART 3 (2 minutes): Afformations following Noah St. John's method. Open-ended "Why am I so naturally..." questions tied to my Gene Keys gift expressions. The questions trigger the subconscious search engine effect. 6 to 8 afformations total.

PART 4 (2 minutes): Integration. Combine my Sun sign, Moon sign, Rising sign energies in a closing visualization. End with one anchoring "I am" statement and a soft return to breathing.

Tone: warm, slow, intimate. Designed to bypass the analytical mind. Include pause indicators in brackets like [pause 3 seconds] where the voice should rest. Length should land around 1200 to 1500 words total spoken.

Generate the full script now.

Claude will produce a script. Read it. Adjust as needed (you know yourself best). Save the final version as jeff_demo_script_v1.md in the AFFIRMOLOGY folder.

Day 2 · Voice Rendering

Bring the script to audio.

Day 2, Morning · 2 hours

Step 1: Set up ElevenLabs and choose a voice

Sign up at elevenlabs.io. Subscribe to Creator tier ($22/mo, 100K characters). Go to Voice Library.

Recommended pre-trained voices for spiritual/affirmation content:

  • Sarah (female, warm, contemplative) - great for general affirmations
  • Charlotte (female, soft, slightly British, intimate) - excellent for personal/healing content
  • Brian (male, calm, deep, slow) - good for meditation guidance
  • Will (male, warm, conversational) - good for friendlier affirmation styles

Generate a 30-second test with each candidate voice using your first paragraph. Listen back. Pick the one that lands.

Day 2, Afternoon · 3 hours

Step 2: Generate the voice track

In ElevenLabs, paste your script in chunks (paragraph by paragraph works best for control). Adjust the Stability slider to around 50 (balanced) and the Style slider to around 30 (some emotion but not too dramatic).

For pause indicators in the script, use SSML break tags:

<break time="3s" />

Or just paste two periods and a space ".. " which ElevenLabs interprets as a natural pause.

Download each chunk as MP3. Stitch them together later, or generate the whole script at once if it fits in one request.

Pro tip: if a section sounds off, regenerate it. ElevenLabs is non-deterministic. Sometimes you get a magical take on the third try. Worth the 30 seconds.
Day 3 · Music & Mix

Layer the music bed and finalize.

Day 3, Morning · 2 hours

Step 1: Generate music with Suno

Sign up at suno.com. Subscribe to Pro ($10/mo for commercial license).

Use these prompt variations to generate 4 to 6 music options:

Suno Prompts to Try "Ambient meditation music, soft piano, gentle pads, 528hz solfeggio frequency feeling, 8 minutes, no vocals, hypnotic, deeply relaxing"

"Celestial cosmic ambient, ethereal female choir pads (wordless), gentle synth swells, slow tempo, 7 minutes, healing frequency"

"Heart-opening meditation bed, soft strings, subtle bell tones, warm low-end, intimate, slow build, 8 minutes"

"Sacred sound healing, crystal bowl tones, gentle drone, breath-paced pacing, 7 minutes, hypnotic"

Pick your favorite, download as WAV or high-quality MP3.

Day 3, Afternoon · 3 hours

Step 2: Mix voice and music

Option A: Descript (Easiest)

  1. Sign up at descript.com
  2. Create new project
  3. Import voice MP3 (top track) and music MP3 (bottom track)
  4. Drag music to start at 0:00, voice to start at ~0:08 (let music breathe first)
  5. Right-click music track, set volume to -18db or -22db (subtle behind voice)
  6. Add fade-in to music (first 5 seconds), fade-out at end (last 10 seconds)
  7. Export as MP3

Option B: FFmpeg (Command Line)

ffmpeg -i voice.mp3 -i music.mp3 \
  -filter_complex \
  "[0:a]volume=1.0[a0]; \
   [1:a]volume=0.20[a1]; \
   [a0][a1]amix=inputs=2:duration=longest" \
  -c:a libmp3lame -b:a 192k \
  affirmology_demo_v1.mp3

Option C: Audacity (Free GUI)

  1. Open Audacity, drag voice MP3 into the project
  2. Drag music MP3 into the project (creates second track)
  3. Lower music track gain to about -18db
  4. Use Effect > Fade In on music track start, Fade Out on music track end
  5. File > Export > Export as MP3
Quality check: listen to the full demo on headphones AND on phone speaker. Both matter. Phone speaker is what most people will hear it on first. If the music drowns out the voice on phone speaker, lower the music volume.
Day 4 (Optional) · Iterate & Polish

Test it on a real person and refine.

Day 4 · 3 to 5 hours

Test, get feedback, regenerate weak sections

  1. Play the demo for Sol or one trusted friend (not Colin or Josh, save them for the polished version).
  2. Watch their face during it. Note where they engage, where they zone out, where they react emotionally.
  3. Ask: "What landed? What felt off? What would you change?"
  4. Identify the 1 or 2 sections that need rework.
  5. Go back to Claude, regenerate that section of script with adjusted tone.
  6. Re-render that section in ElevenLabs.
  7. Splice it into the existing demo (Descript or Audacity).
  8. Re-export.
The 80/20 of demo quality: the first 90 seconds is what wins or loses the listener. If the heart coherence intro and the first 2 to 3 affirmations land hard, the rest of the audio gets the benefit of the doubt. Spend extra time on the opening.
Showing the Demo

How to use it in your meetings.

Sunday with Josh

Wait until hour 2 or 3 of the meeting. Once you have shown him the deck and the term sheet and he is engaged: "I built a demo of the product. I want you to listen to 5 minutes of it on headphones right now." Hand him your phone with the audio queued up. Watch his face. Do not talk. Let the audio do the work.

Thursday with Colin

Tell him over Zoom: "I built a working demo of the product using my own data. Want me to send you the file to listen to before our next conversation?" Send it after the call. Follow up with a question: "What did you think when you listened?"

Omaha with Steve, Laura, Chris

Same approach as Josh. Phone with headphones. Personal data. Live listening. Reaction.

Faena Conference

If the demo is good enough by September, set up a booth with 4 to 6 headphone sets. Each visitor enters their birth data on a tablet, hits "generate sample," gets a 90-second personalized clip queued up automatically. This is the activation flow. The 5-minute Sunday demo is the proof that the activation flow is possible.

After the Demo

What this unlocks for the next phase.

Once the manual demo works and gets reactions, the agent automation work becomes meaningful instead of speculative. You have proven the product end to end. The next phase (post-funding) is wrapping the manual steps in agent orchestration:

This is the architecture Claude Code can help you build over a 30 to 60 day sprint once the round closes. The manual demo proves the pieces work. The agents just make it scalable.

Realistic Timeline

If you start tomorrow.

Camp Brotherhood constraint: if Camp Brotherhood is on the calendar between now and Sunday, this whole plan compresses or shifts. Tell me the dates and we can adjust. If Camp Brotherhood is AFTER Sunday, you have a clear runway. If it is the weekend, the demo build needs to happen Monday through Friday.