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
Understanding Transcription Speed
When you release the hotkey, there is a short delay before your text appears. This is completely normal — Weesper Neon Flow is transcribing your audio locally on your device, and the time it takes depends on three factors:
| Factor | Impact on Speed | Impact on Accuracy |
|---|---|---|
| AI model (Minimal → Small) | Larger models are slower | Larger models are more accurate |
| Accuracy level | Higher accuracy takes longer | Better transcription quality |
| Your hardware (CPU, RAM) | Faster hardware = faster results | No impact |
The Speed–Quality Tradeoff
Think of it as a triangle: model power, accuracy, and hardware. You control the first two — adjust them to match your hardware:
- Powerful machine (Apple Silicon, modern CPU, 16 GB+ RAM) → Use Small model + high accuracy for best results with minimal delay
- Mid-range machine (8 GB RAM) → Base model + medium accuracy is the sweet spot
- Older hardware (4 GB RAM, older CPU) → Tiny or Minimal model + lower accuracy for responsive dictation
Finding Your Sweet Spot
If transcription feels too slow after you release the hotkey:
- Go to Settings → Quality & Speed
- Try a lighter model first — switch from Small to Base, or Base to Tiny
- Then adjust accuracy — lower it one step and test again
- Repeat until you find the right balance between speed and quality
The best configuration is the one where you barely notice the delay while still getting accurate transcriptions. Test with a few short sentences after each change.
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