### Install ViolaWake SDK with OpenWakeWord extra

Source: https://violawake.com/docs

Install the SDK with the 'oww' extra to enable the OpenWakeWord runtime backbone required for wake detection.

```bash
pip install "violawake[oww]"
```

--------------------------------

### Train custom wake word with violawake-train CLI

Source: https://violawake.com/docs

Train a custom wake word model using the CLI, specifying the word, positive samples directory, and output path.

```bash
violawake-train --word "jarvis" --positives samples/jarvis --output models/jarvis.onnx
```

--------------------------------

### Detect wake word with WakeDetector

Source: https://violawake.com/docs

Use the WakeDetector class to stream from the microphone and detect a wake word using a TemporalCNN model with a threshold of 0.80. Prints a message when detected.

```python
from violawake_sdk import WakeDetector

with WakeDetector(model="temporal_cnn", threshold=0.80) as detector:
    for chunk in detector.stream_mic():
        if detector.detect(chunk):
            print("Wake word detected")
            break
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.