Audio and podcasting decision
DeeVee
A technical user can reproduce the core AI search and playback experience in ~30 hours using an existing self-hosted server (Audiobookshelf) plus embeddings and a vector DB; the main durable value to the vendor is curated premium content which you won't get.
View on the App Store↗$9.99/mo
$120/yr
Read off the official pricing page.
$50one-off30 h to build
$90/mo6 h/mo upkeep
On cash alone, building overtakes the subscription at 10 seats.
The code exists. It is not what you are paying for.
These 2 projects are real, published, and do the core job — and this page still says keep paying. What the subscription buys is content rights and content rights, and none of that ships in a repository. Fork one anyway if you want to. Go in knowing what it does not carry. What stays hard ↓ · All DeeVee alternatives, with the arithmetic →
What a replacement has to do
- Index audio story transcripts, generate embeddings, run natural-language search over a vector DB, stream audio via a player, and save favorites/playlists.
What it still won’t have
- Polished native iOS app and App-Store UX
- Curated premium catalog labeled “DV Stories” and any curated licensing the vendor holds
- Any proprietary AI models or backend optimizations the vendor runs
- Built-in App Store subscription plumbing and reviews/ratings
What remains hard
- Content rights
DV Stories: curated premium audio content
- Content rights
Content from trusted platforms and creators
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 10 seats.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a web-based AI audio-discovery service using Audiobookshelf for media hosting, PostgreSQL for metadata, Pinecone (or Milvus) for vector storage, and OpenAI embeddings. Core features in scope: ingest audio and transcripts, periodic transcription job (Whisper/OpenAI), generate embeddings and index them in the vector DB, natural-language search API that returns ranked results with match percentage, simple web player with queue and favorites, and Stripe-based subscription gating for premium content. Out of scope: native iOS client, building a curated premium catalog (DV Stories), and training new ML models. Include error handling, retries for external API calls, unit tests for the search API, and deployment scripts (Docker + docker-compose or Kubernetes manifests).
How we checked
How the score was reached
- Pay verdict base20
- An open-source build was found+5
- 3 cited sources+3
- Price verified on pricing page+3
- Hard moats found in the evidence-3
- Evidence score28
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 3
Every page the run actually retrieved.
- official productDeeVee: Audio Stories Search - App Store
- open sourceadvplyr/audiobookshelf
- open sourceChevron7Locked/kima-hub
Integrity checks
What held up, and what did not.
