Workload guide · AI
Voice assistant (local): hardware requirements guide
Local STT/TTS and wake-word (Whisper, Piper, Rhasspy).
Hardware requirements by tier
Three tiers for every workload: the minimum that works, the recommended sweet spot, and the comfortable headroom level. These are the same tiers the WisePC decision engine uses when it plans a build around your goal.
| Tier | CPU cores | RAM | Storage | GPU | Network |
|---|---|---|---|---|---|
| Minimum | 4 cores | 8 GB | 0.5 TB (ssd) | None | 1 GbE |
| Recommended | 8 cores | 16 GB | 1 TB (ssd) | dedicated | 1 GbE |
| Comfortable | 12 cores | 32 GB | 1 TB (ssd) | ai | 2.5 GbE |
Which tier do you need?
- Pick Minimum (4 cores, 8 GB RAM) only for a single-purpose machine on a tight budget — expect little headroom.
- Recommended (8 cores, 16 GB RAM) is the sweet spot: enough for the workload plus the usual side-services, without overspending.
- Pick Comfortable (12 cores, 32 GB RAM) when this workload shares the machine with others or will grow — you pay for headroom, not for anxiety.
- GPU rule for this workload: dedicated.
Frequently asked questions
How much RAM does voice assistant (local) need?
8 GB is the sensible minimum, 16 GB covers most real setups, and 32 GB gives comfortable headroom for growth and extra services.
How many CPU cores does voice assistant (local) need?
A 4-core CPU is the minimum, 8 cores is the recommended sweet spot, and 12 cores is comfortable when it shares the machine with other workloads.
Does voice assistant (local) need a dedicated GPU?
A dedicated GPU is required for this workload.
What storage and network does voice assistant (local) expect?
Storage: 1 TB of SSD is the recommended baseline (0.5 TB minimum, 1 TB comfortable). Network: 1 GbE is the recommended baseline.
What runs well alongside voice assistant (local)?
It pairs naturally with: Home Assistant, Local AI inference.