# AI smart codec

Source: [https://docs.qualcomm.com/doc/80-70022-50/topic/ai-smart-codec.html](https://docs.qualcomm.com/doc/80-70022-50/topic/ai-smart-codec.html)

The **gst-ai-smartcodec-example** application reduces network bandwidth and
        storage resources for input from a camera or a file source.

## Sample model and label files

Table : Sample model and label files for gst-ai-smartcodec-example

| Runtime | Model files | Label files |
| :--- | :--- | :--- |
| LiteRT | <var class="keyword varname">YOLOv8-Detection-Quantized.tflite</var> | <var class="keyword varname">coco_labels.txt</var> |

## Run the application on the target device

For model and label files, see Sample model and label files.

1. Ensure that you complete the Prerequisites.
2. Use one of the following sources to run the application:
    - Run the application with a camera
                            source:

            gst-ai-smartcodec-example -w 640 -h 480 -o output.mp4 -m /etc/models/YOLOv8-Detection-Quantized.tflite -l /etc/labels/coco_labels.txtCopy to clipboard
    - Run the application with a file
                            source:

            gst-ai-smartcodec-example -i /etc/media/video.mp4 -o output.mp4 -m /etc/models/YOLOv8-Detection-Quantized.tflite -l /etc/labels/coco_labels.txtCopy to clipboard
3. To display the available help options, run the following commands in the SSH
                        shell:

        gst-ai-smartcodec-example --helpCopy to clipboard
4. To stop the use case, use CTRL +
                            C.

## Expected output

The application generates the output as an encoded MP4 file.

## Related information

Smart codec

**Parent Topic:** Run AI/ML sample applications

Last Published: Feb 20, 2026

Previous Topic
 
Multistream batch inference Next Topic

Face detection