Meeting Voice Notes

A voice memo task extractor app idea: a voice memo turner that pulls tasks out of rambling audio. Weekend build with Python, faster-whisper, Flask and Claude API, for solo consultants who dictate notes after client calls.

See the spec
Why now

Why now

faster-whisper is up 179% in weekly PyPI downloads, which makes local, fast transcription easy to run on a laptop. Nvidia's NVIDIA-Nemotron-3.5-Transcribe-30B-A4B is also trending on Hugging Face for speech recognition. From the signals of the week of 26 Oct 2026.

The spec

The spec

Drop in a voice memo recorded after a client call and get a clean list of action items, who owns each, and any dates mentioned. It solves the problem of good notes sitting unlistened in a phone.

Build time

WeekendBasic logic / CRUD · Level 2 of 5

Audience

Solo consultants who dictate notes after client calls.

Stack

  • Python
  • faster-whisper
  • Flask
  • Claude API

Fun factor

You talk at your phone while walking and get a tidy to-do list back minutes later.

Core features

  • Drag and drop audio upload
  • Transcript with timestamps
  • Editable action item list
  • Export to Markdown or CSV

AI features

  • Transcribe audio locally with faster-whisper
  • Extract tasks, owners and due dates from the transcript with an LLM and link each to its timestamp

Stretch goals

  • Email the task list to the client
  • Recurring client memory so names resolve correctly
  • Push tasks to Todoist or Linear

First version

Upload one audio file, get a transcript and a checkbox list of action items with timestamps.

Build plan

Build plan

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

Transcribe a fileRun faster-whisper on an uploaded memo and show the text.
Start here
Extract tasksPrompt an LLM to return structured JSON with task, owner and date.
Build the checklist UIRender tasks with checkboxes and timestamp links.
Add exportOffer Markdown and CSV downloads.
The build prompt

The build prompt

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

meeting-voice-notes.prompt.md
# Build Meeting Voice 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

**Meeting Voice Notes.** Drop in a voice memo recorded after a client call and get a clean list of action items, who owns each, and any dates mentioned. It solves the problem of good notes sitting unlistened in a phone.

**Why now:** faster-whisper is up 179% in weekly PyPI downloads, which makes local, fast transcription easy to run on a laptop. Nvidia's NVIDIA-Nemotron-3.5-Transcribe-30B-A4B is also trending on Hugging Face for speech recognition.

**Who it is for:** Solo consultants who dictate notes after client calls

**What makes it fun:** You talk at your phone while walking and get a tidy to-do list back minutes later.

## Scope

- **Build time:** Weekend. Size every decision to ship a working first version inside this window.
- **Technical ambition:** Level 2 of 5, "Basic logic / CRUD". A few screens over a simple data model with create, read, update, and delete. One lightweight persistence layer, no heavy infrastructure.
- **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. Drag and drop audio upload
2. Transcript with timestamps
3. Editable action item list
4. Export to Markdown or CSV

## AI features

- Transcribe audio locally with faster-whisper
- Extract tasks, owners and due dates from the transcript with an LLM and link each to its timestamp

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)

- Email the task list to the client
- Recurring client memory so names resolve correctly
- Push tasks to Todoist or Linear

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: Python, Faster-whisper, Flask, 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: Upload one audio file, get a transcript and a checkbox list of action items with timestamps.

## Build plan (with saved progress)

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

1. **Transcribe a file** [not started]
   Run faster-whisper on an uploaded memo and show the text.

2. **Extract tasks** [not started]
   Prompt an LLM to return structured JSON with task, owner and date.

3. **Build the checklist UI** [not started]
   Render tasks with checkboxes and timestamp links.

4. **Add export** [not started]
   Offer Markdown and CSV downloads.

## Definition of done for the first version

- [ ] Drag and drop audio upload works end to end, with real data, not a placeholder.
- [ ] Transcript with timestamps works end to end, with real data, not a placeholder.
- [ ] Editable action item list works end to end, with real data, not a placeholder.
- [ ] Export to Markdown or CSV 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 Meeting Voice Notes is, how to build it, and where example ideas come from.

Similar ideas

Similar to Meeting Voice Notes

More ai tools 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.