Recording a meeting and running it through a speech-to-text API gets you a real transcript in a weekend — that part is thoroughly solved. Accurately labeling who said what, and summarizing it well, is where the real product work is.
VIBE SCORE 93/100
The parts this build actually needs, each rated on its own — the average is the Vibe Score above.
| Landing page | 99 |
| CRUD database | 95 |
| Search | 86 |
Two real costs, not just "free": the AI agent's own usage, and hosting once it's running. Both are estimated from this app's own effort rating and component list — see the assumptions on the method page.
| AI agent — with a subscription (Claude Pro/Max, Cursor, etc.) | $0 marginal |
| AI agent — pay-per-use API, no subscription | $43–$86 one-time |
| Hosting, once it's running | $0/mo (free tier) |
| Domain name, if you want your own | ~$12/yr |
Otter.ai costs $16.99/mo. Even paying per-token with no subscription, and accounting for hosting, this build pays for itself in about 6 months.
Borderline. Recording a meeting and running it through a speech-to-text API gets you a real transcript in a weekend — that part is thoroughly solved. Accurately labeling who said what, and summarizing it well, is where the real product work is.
Otter.ai costs $16.99/mo (about $204/yr) as of 2026-08. That's what a working rebuild would save you.
Speaker diarization (correctly labeling who said what across a call with multiple voices) is a genuinely hard audio-ML problem most transcription APIs handle with varying accuracy Live, real-time transcription during a call (not after-the-fact) needs streaming audio infrastructure Calendar integration that auto-joins scheduled meetings to record them is real per-platform integration work