Cost Simulator — Voice Pipeline
Estimate the real monthly cost of your voice pipeline (STT + RAG + LLM + TTS) accounting for subscription plans, included minutes, top-ups, and parallel stream limits.
Start with a preset
Usage Volume
Set the number of users and session duration — total minutes are computed automatically. Parallel streams define simultaneous capacity and may trigger plan alerts.
1 — Speech Recognition (STT)
2 — Knowledge Base (RAG)
3 — Language Model (LLM)
4 — Voice Synthesis (TTS)
Simulation Results
The “Free (Google AI Studio)” plan includes 0 min but allows no overage. Your volume (2,500 min/mo) exceeds this by 2,500 min — “Pay As You Go” plan selected automatically.
The “Free” plan includes 20 min but allows no overage. Your volume (2,500 min/mo) exceeds this by 2,480 min — “Pay as you go · v4 Turbo” plan selected automatically.
| Component | Provider | $/min (optimal plan) | Selected plan | $/user (plan) | Total/mo |
|---|---|---|---|---|---|
| STT | Deepgram Nova-3 | $0.00480 | Pay As You Go | $0.048 | $12 |
| RAG | Voyage AI + Supabase pgvector | $0.00002 | Free + Supabase Free | $0.00020 | $0.05+$25 |
| LLM | Gemini 2.5 Flash | $0.00195 | Pay As You Go | $0.019 | $5 |
| TTS | Eleven v4 / v4 Turbo | $0.040 | Pay as you go · v4 Turbo | $0.400 | $100 |
| Total (optimal plans) | $0.468 | $142 | |||
| OPTIMAL TOTAL (best plans) | — | $142 | |||
Preset comparison at your volume
Estimated monthly cost for 250 users × 10 min/session = 2,500 min/month. 10 parallel streams.
| Preset | STT | RAG | LLM | TTS | $/user | Total/mo | Latency | EU | Streams |
|---|---|---|---|---|---|---|---|---|---|
Storygami — Optimal | $12 | $0.05+$25 | $5 | $100 | $0.468 | $142 | 625ms | ∞ | |
Storygami — Budget | $6 | $0.05+$25 | $5 | $63 | $0.295 | $99 | — | ∞ | |
Edugami — Optimal | $5 | $0.05+$25 | $2 | $40 | $0.188 | $72 | 769ms | ∞ | |
Sovereign EU Stack | $26 | $0.05+$25 | $2 | $108 | $0.545 | $161 | 686ms | 15 | |
Self-Hosted (Open-Source) | $0.00 | $0.00 | $0.00 | $0.00 | $0.00000 | $0.00 | 650ms | ∞ |