Available Models
Weesper Neon Flow includes several AI transcription profiles:
| Profile | Accuracy | Speed | RAM Usage | Best For |
|---|---|---|---|---|
| Minimal | Basic | Fastest | ~500 MB | Low-end hardware |
| Tiny | Good | Very fast | ~1 GB | Quick notes |
| Base | Better | Fast | ~1.5 GB | Daily use (recommended) |
| Small | Best | Moderate | ~2 GB | Professional use |
How to Change Models
- Open Settings → Quality & Speed
- Select your preferred profile
- The model loads automatically for your next dictation
Recommendations
- Apple Silicon Mac (M1+): Use Base or Small for the best experience
- Intel Mac / Windows: Base is the sweet spot
- Older hardware (4 GB RAM): Use Tiny or Minimal
- Professional / medical / legal: Use Small for highest accuracy
Smart Pause Detection
Enable Smart Pause Detection in Settings → Quality & Speed for a 20-30% speed boost. The engine automatically skips silent moments in your recording.
Related
- Improving Accuracy — Tips beyond model selection
- Custom Dictionary — Add domain-specific vocabulary
- System Requirements — Check RAM and hardware recommendations