# Build brief — a focused alternative to Swell AI

> **Verdict:** Yes, for personal use · **Buildability:** 76/100 · **Category:** Podcasting
> **Source:** https://www.canitbevibecoded.com/swell-ai
> Independent editorial assessment from Can It Be Vibe Coded? Not affiliated with, endorsed by, or derived from Swell AI. Verify current pricing and capabilities before acting.

## Context

**Swell AI** — Generate show notes, articles, social posts, and transcripts from uploaded episodes. It currently costs $17/mo.

The core loop is small enough for a capable coding agent to produce a useful local version. For Swell AI, generate show notes, articles, social posts, and transcripts from uploaded episodes. The hard boundary is templates, integrations, hosted processing, and content history, plus audio infrastructure, distribution, and production polish.

This brief describes a focused, single-operator replacement for the part of Swell AI that is genuinely reproducible. It is deliberately narrower than the product it replaces, and it says so in writing. Build the useful core; do not pretend to have rebuilt the rest.

## What you are building

Import spoken-word episode audio, perform practical cleanup, generate transcripts, show notes, articles, and social posts, and export production files.

- Build a focused single-user workflow with real persistence, search, and export.
- A responsive interface with real empty, loading, success, and error states.

## Requirements

### Functional

- Ffmpeg.
- Local audio files.
- Sufficient disk space.

### Data and integrations

- Optional transcription API key.

Each of these needs a real account, credential, or quota. Set them up before writing feature code.

### Non-functional

- Accessibility: semantic markup, labelled controls, visible focus, and reduced-motion support.
- Security: server-side secrets, validated input, and no credentials in the client bundle.
- Reliability: retries with backoff on external calls, and a clear failure state when a provider is down.
- Portability: the operator can export their data and leave without losing it.

## Implementation brief

Build a personal replacement for Swell AI in an empty repository.
Use Python 3.12, FastAPI, ffmpeg, SQLite, and an HTMX interface; do not offer alternative stacks.
The core loop is: import spoken-word episode audio, perform practical cleanup, generate transcripts, show notes, articles, and social posts, and export production files.
Make the first run work locally with one documented command.
Store all user data locally by default and make export straightforward.
Put secrets in .env, ship .env.example, and never commit credentials.
Create an upload queue and preserve originals in a read-only media folder.
Generate waveforms and non-destructive edit markers instead of rewriting source files.
Implement silence trimming, loudness normalization to -16 LUFS, fades, and noise-gate presets.
Add chapter markers, intro and outro slots, and a simple two-track timeline.
Produce a transcript and draft title, description, chapters, and social excerpts.
Export MP3, WAV, transcript, chapters JSON, and a complete project manifest.
Include clear empty, loading, success, and recoverable error states.
Add input validation, safe filenames, and graceful handling of unavailable APIs.
Write focused tests for the core transformation and one end-to-end happy path.
Create a README with setup, architecture, permissions, data location, and backup steps.
Do not add accounts, billing, telemetry, analytics, or a hosted control plane.
Deliberately leave out real-time remote recording.
Deliberately leave out podcast hosting and directory analytics.
Deliberately leave out licensed stock music and voice cloning.
Finish by running the tests and listing the exact commands used.

## Delivery standard

- Inspect the repository first, then write a short implementation plan before writing code.
- Deliver the smallest complete end-to-end workflow first; every primary control must work against persisted data.
- Use real validation and storage; never substitute fake dashboards, decorative controls, hard-coded success states, or mock integrations.
- Include responsive layouts plus genuine empty, loading, success, validation, and failure states.
- Keep secrets server-side in environment variables, provide .env.example, and never commit credentials or user data.
- Add structured logs around every external call and return actionable errors without leaking sensitive details.
- Write unit tests for the core logic and one automated test of the main user journey.
- Finish with a README covering setup, architecture, data location, backups, tests, deployment, and known limitations.

## Acceptance criteria

- [ ] A clean install starts the app using only the README and .env.example.
- [ ] The primary journey works from first visit through saved result, reload, edit, export, and deletion where applicable.
- [ ] Invalid input, missing configuration, provider failure, and an empty database each have a usable state.
- [ ] The interface works at 390px and 1440px, is keyboard navigable, and shows visible focus on every control.
- [ ] Tests, type checking, linting, and a production build all pass with no ignored failures.
- [ ] No part of the interface implies a live integration, security guarantee, or scale capability that was not actually built and verified.

## Non-goals

Do not build these, and do not claim to have replaced them:

- Templates, integrations, hosted processing, and content history.
- Remote studio reliability.
- Licensed music libraries.
- Hosting distribution.
- Reliability at the vendor's scale is an operations problem, not a prompt.
- The last 20 percent is sync, migration fidelity, speed, and edge cases.

## What you still own after launch

- Secure credentials, rotate secrets, and handle provider rate limits.
- Run migrations, backups, restores, and dependency updates.
- Test the critical journey after every model, API, or hosting change.
- Monitor failures and fix the edge cases a first prompt will miss.

## Risk

**Operational risk.** The code is achievable; dependable data, integrations, and ongoing operations are the real cost.

Editorial confidence in this assessment: high. No independent one-shot implementation is linked yet.

## Prior art

Working open-source software you can read, fork, or borrow from before starting:

- [Audacity](https://github.com/audacity/audacity) — Long-running open-source multitrack audio editor and useful implementation prior art

---

Generated by [Can It Be Vibe Coded?](https://www.canitbevibecoded.com) · Full report: https://www.canitbevibecoded.com/swell-ai