Whisper Tally
A meeting transcript analytics app idea: a dashboard that counts what gets said across your calls. One week build with Python, faster-whisper, Flask and Claude API, for founders and product managers who record customer calls.
Why now
faster-whisper is up 208% on PyPI against the rest of the month and whisper is up 119%, so local transcription is cheap and easy. Screen Studio 4.0 and Empacer both show people recording and talking more to their tools, which leaves a lot of audio nobody reviews. From the signals of the week of 9 Nov 2026.
The spec
Transcribes a folder of call recordings locally, then charts how often topics, objections and feature requests come up over time. It turns a pile of recordings into numbers you can use in a roadmap meeting.
Build time
One weekAPIs or integrations · Level 3 of 5Audience
Founders and product managers who record customer calls.
Stack
- Python
- faster-whisper
- Flask
- Claude API
Fun factor
Seeing a complaint you half remembered turn into a rising line is oddly satisfying.
Core features
- Folder watch and local transcription
- Topic and keyword frequency charts by week
- Objection and feature request tagging
- Click a data point to read the source quote
AI features
- Clusters transcript sentences into topics without a preset list
- Labels each cluster as objection, request, praise or question
Stretch goals
- Compare segments such as trial and paying customers
- Export a weekly summary to Slack
- Speaker separation
First version
A local app that transcribes a folder of audio and shows a weekly topic count chart with quotes.
Build plan
4 milestones, in the order you would build them. Saved ideas get this plan with checkboxes and notes.
The build prompt
Paste this into ChatGPT, Claude, Codex, or Cursor, then build the first version before anything else.
# Build Whisper Tally 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 **Whisper Tally.** Transcribes a folder of call recordings locally, then charts how often topics, objections and feature requests come up over time. It turns a pile of recordings into numbers you can use in a roadmap meeting. **Why now:** faster-whisper is up 208% on PyPI against the rest of the month and whisper is up 119%, so local transcription is cheap and easy. Screen Studio 4.0 and Empacer both show people recording and talking more to their tools, which leaves a lot of audio nobody reviews. **Who it is for:** Founders and product managers who record customer calls **What makes it fun:** Seeing a complaint you half remembered turn into a rising line is oddly satisfying. ## 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. Folder watch and local transcription 2. Topic and keyword frequency charts by week 3. Objection and feature request tagging 4. Click a data point to read the source quote ## AI features - Clusters transcript sentences into topics without a preset list - Labels each cluster as objection, request, praise or question 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) - Compare segments such as trial and paying customers - Export a weekly summary to Slack - Speaker separation 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: A local app that transcribes a folder of audio and shows a weekly topic count chart with quotes. ## Build plan (with saved progress) 0 of 4 steps complete. Resume at step 1: Transcribe a folder. Before you start it, check what is already implemented so you do not repeat finished work. 1. **Transcribe a folder** [not started] Run faster-whisper on new files and store text with timestamps. 2. **Cluster topics** [not started] Group sentences and name each cluster with the model. 3. **Chart over time** [not started] Show weekly counts per topic in a simple Flask page. 4. **Link to quotes** [not started] Let a click on any bar open the matching lines. ## Definition of done for the first version - [ ] Folder watch and local transcription works end to end, with real data, not a placeholder. - [ ] Topic and keyword frequency charts by week works end to end, with real data, not a placeholder. - [ ] Objection and feature request tagging works end to end, with real data, not a placeholder. - [ ] Click a data point to read the source quote 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
- Copy the prompt above.
- Open ChatGPT, Claude, or your AI editor and paste it into a new conversation.
- 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.
FAQ
Frequently asked questions
Answers on what Whisper Tally is, how to build it, and where example ideas come from.
Similar to Whisper Tally
More data & analytics ideas, then a few from other categories.
Ready to generate yours?
Four ideas per round, shaped by your interests, skill level, and how much time you have.