Voice Pipeline Notes

A small business voice CRM app idea: a voice-first deal tracker for solo service sellers. One week build with Next.js, Supabase, faster-whisper and Claude API, for solo consultants and tradespeople who sell between jobs.

See the spec
Why now

Why now

Empacer: The voice-first assistant for small business owners hit 453 upvotes on Product Hunt, showing demand for talking instead of typing. Nvidia's NVIDIA-Nemotron-3.5-Transcribe-30B-A4B and faster-whisper make accurate transcription easy to run. From the signals of the week of 26 Oct 2026.

The spec

The spec

Speak a quick note after a call or site visit and it updates the right deal, sets the next step and flags deals gone quiet. It removes the habit of typing CRM entries that never get done.

Build time

One weekAPIs or integrations · Level 3 of 5

Audience

Solo consultants and tradespeople who sell between jobs.

Stack

  • Next.js
  • Supabase
  • faster-whisper
  • Claude API

Fun factor

Talking to your pipeline in the van and seeing the board update itself feels like cheating.

Core features

  • Record a note from phone browser
  • Deal board with stages
  • Next-step date and reminder
  • Quiet-deal list after seven days

AI features

  • Match a spoken note to the right deal by name and context
  • Extract next step, price mentioned and objections into structured fields

Stretch goals

  • Draft follow-up text message from the note
  • Calendar sync
  • Weekly pipeline summary by voice

First version

Record a note, see it transcribed and attached to a deal card with a next-step date.

Build plan

Build plan

4 milestones, in the order you would build them. Saved ideas get this plan with checkboxes and notes.

Build the boardCreate deals and stages with plain CRUD.
Start here
Add recordingCapture audio in the browser and transcribe it.
Parse notesExtract deal match, next step and date as JSON.
Add nudgesList deals with no activity for seven days.
The build prompt

The build prompt

Paste this into ChatGPT, Claude, Codex, or Cursor, then build the first version before anything else.

voice-pipeline-notes.prompt.md
# Build Voice Pipeline Notes

You are a senior full-stack engineer pairing with me on a side project. Build a working first version of the product described below. Read the whole brief before writing any code, then follow "How to work" at the end.

## The idea

**Voice Pipeline Notes.** Speak a quick note after a call or site visit and it updates the right deal, sets the next step and flags deals gone quiet. It removes the habit of typing CRM entries that never get done.

**Why now:** Empacer: The voice-first assistant for small business owners hit 453 upvotes on Product Hunt, showing demand for talking instead of typing. Nvidia's NVIDIA-Nemotron-3.5-Transcribe-30B-A4B and faster-whisper make accurate transcription easy to run.

**Who it is for:** Solo consultants and tradespeople who sell between jobs

**What makes it fun:** Talking to your pipeline in the van and seeing the board update itself feels like cheating.

## Scope

- **Build time:** One week. Size every decision to ship a working first version inside this window.
- **Technical ambition:** Level 3 of 5, "APIs or integrations". The product leans on third-party APIs. Wrap each integration in its own module, handle its failures and rate limits, and cache what is safe to cache.
- **First version only.** Ship the core features below end to end. Stretch goals are listed so you can design around them, not build them.

## Core features (each must work end to end in the first version)

1. Record a note from phone browser
2. Deal board with stages
3. Next-step date and reminder
4. Quiet-deal list after seven days

## AI features

- Match a spoken note to the right deal by name and context
- Extract next step, price mentioned and objections into structured fields

How to build them:
- Put every model call behind one server-side module with a typed interface, so the provider can change without touching the UI.
- Read API keys from environment variables only, and document each one in `.env.example`.
- Write prompts as versioned constants with clear instructions and an example of the expected output; parse and validate responses before using them.
- Handle timeouts, rate limits, and malformed output with a graceful fallback the user can understand. Stream responses where a wait would exceed a couple of seconds.
- Never let a feature depend on the model being perfect. Show the result, let the user edit or retry.

## Stretch goals (later, not in the first version)

- Draft follow-up text message from the note
- Calendar sync
- Weekly pipeline summary by voice

Leave clean seams for these (a module boundary, a nullable column, a feature flag), but do not implement them unless I ask.

## Tech stack

Use exactly: Next.js, Supabase, Faster-whisper, Claude.

Stay on current stable versions, follow each tool's official conventions, and add a library only when the standard library or the chosen stack cannot do the job cleanly. If part of this stack is a poor fit for a specific requirement, say so and propose the smallest change.

## Owner's notes

Written by me, the project owner. Treat these as requirements and preferences that override the generated material above when they conflict.

The first version should be exactly this, and no bigger: Record a note, see it transcribed and attached to a deal card with a next-step date.

## Build plan (with saved progress)

0 of 4 steps complete. Resume at step 1: Build the board. Before you start it, check what is already implemented so you do not repeat finished work.

1. **Build the board** [not started]
   Create deals and stages with plain CRUD.

2. **Add recording** [not started]
   Capture audio in the browser and transcribe it.

3. **Parse notes** [not started]
   Extract deal match, next step and date as JSON.

4. **Add nudges** [not started]
   List deals with no activity for seven days.

## Definition of done for the first version

- [ ] Record a note from phone browser works end to end, with real data, not a placeholder.
- [ ] Deal board with stages works end to end, with real data, not a placeholder.
- [ ] Next-step date and reminder works end to end, with real data, not a placeholder.
- [ ] Quiet-deal list after seven days works end to end, with real data, not a placeholder.
- [ ] Every screen handles loading, empty, and error states.
- [ ] Typecheck, lint, and any tests pass, and the main user flow was exercised by hand.
- [ ] A README explains setup, environment variables, and how to run it locally.

## Quality bar

- Responsive from a phone to a desktop, keyboard-accessible, semantic HTML, visible focus states, labelled inputs, and sensible contrast.
- Loading, empty, and error states for every screen that reads or writes data. Errors say what happened and what to do next.
- Validate on the server, never trust the client, and keep secrets in environment variables with a committed `.env.example`.
- Type-safe end to end. No `any` without a comment explaining why.
- Small, readable modules named after what they do. No premature abstraction, no dead code, no TODOs left for later without a note.
- Sensible defaults over settings. If a choice is not in this brief, pick the simplest option that keeps the product coherent and say what you chose.

## How to work

1. **Read, then restate.** Summarize the product in three sentences and list your assumptions. Ask only the questions that block implementation. For everything else, decide and note the decision.
2. **Plan before code.** List the files and modules you will create, in build order, mapped to the core features. If a build plan is included above, use it instead: resume at the first step not marked done and check what already exists before touching it.
3. **Set up.** If a project already exists, inspect its code, instructions, and conventions first and build on them. Otherwise scaffold the stack above with linting, formatting, a typecheck script, `.env.example`, and a README stub.
4. **Model the data first.** Define the types, schema, and any migrations before the UI, so the shape of the product is settled early.
5. **Build in vertical slices.** Finish one core feature end to end (data, logic, UI) before starting the next. Keep the app runnable after every slice and commit each slice with a message that says what changed and why.
6. **Then the interface.** Apply the quality bar above to each screen as it lands, not as a final pass.
7. **Verify.** Run typecheck, lint, and tests. Exercise the main user flow by hand. Check each item in the definition of done and each acceptance criterion.
8. **Report.** Tell me what works, what you tested and how, what is not done, every setup step I must complete myself, and the three most useful next steps. Never claim a service, test, or flow was verified when it was not.

If you can edit and run the project, start implementing right after the short plan. If you cannot, give me concrete code and the exact commands to run for the next step.

Rules: keep the product name and the scope as written, do not invent features, prefer boring and proven choices, and stop to ask me when a decision would be expensive to reverse.

How to use

  1. Copy the prompt above.
  2. Open ChatGPT, Claude, or your AI editor and paste it into a new conversation.
  3. Build milestone one, run it, then move to the next. Add stretch goals only after the first version works.

Want ideas built around you instead? Generate four from your own interests, time, and stack.

Frequently asked questions

FAQ

Frequently asked questions

Answers on what Voice Pipeline Notes is, how to build it, and where example ideas come from.

Similar ideas

Similar to Voice Pipeline Notes

More sales ideas, then a few from other categories.

Generate your own

Ready to generate yours?

Four ideas per round, shaped by your interests, skill level, and how much time you have.