Whisper (voice): hardware requirements
Local speech-to-text and wake-word voice assistant.
Hardware tiers
| Tier | CPU | RAM | Storage | GPU | VRAM | Network |
|---|---|---|---|---|---|---|
| Minimum sensible | 4 cores | 8 GB | 0.5 TB (ssd) | None | — | 1 GbE |
| Recommended | 8 cores | 16 GB | 1 TB (ssd) | dedicated | 4 GB VRAM | 1 GbE |
| Comfortable | 12 cores | 32 GB | 1 TB (ssd) | ai | 12 GB VRAM | 2.5 GbE |
| Overkill | 20 cores | 52 GB | 2 TB (ssd) | ai | 12 GB VRAM | 2.5 GbE |
- Minimum sensible: The smallest build that genuinely works — tight, focused, no fluff.
- Recommended: The sweet spot: handles the service plus the usual side-services.
- Comfortable: Real headroom — this service will never be the bottleneck.
- Overkill: More than you will ever use for this service alone — spend the money elsewhere.
Beyond Comfortable — 12 cores, 32 GB RAM, 1 TB: headroom you will never use for this service alone.
Size it exactly
Pick the Whisper size — larger hears better, needs more VRAM.
You need about 4 GB of VRAM for this.
Runs well with
Home Assistant, Local AI inference
Frequently asked questions
How much RAM does Whisper (voice) need?
8 GB is the sensible minimum, 16 GB covers most real setups, and 32 GB gives comfortable headroom.
How many CPU cores does Whisper (voice) need?
4 cores are the minimum, 8 cores the sweet spot, and 12 cores comfortable when shared with other services.
Can I run several services on one machine?
Yes — most services share resources. Use the planner and select several services; the engine sums and overlaps the requirements instead of stacking them.
What if I already have hardware?
Register it in My hardware and the analysis shows exactly which services your current system can comfortably run — including an honest “do nothing”.