# AI smart codec

Source: [https://docs.qualcomm.com/doc/80-70017-50/topic/ai-smart-codec.html](https://docs.qualcomm.com/doc/80-70017-50/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.

## Prerequisites

- [Download model, label and config JSON files for LiteRT and Qualcomm AI Engine direct](https://docs.qualcomm.com/doc/80-70017-50/topic/ai-ml-sample-applications.html#ai-ml-sample-applications__section_fsl_lgz_scc).
- To access your host device, enable SSH. For instructions, see [Log in using SSH](https://docs.qualcomm.com/bundle/publicresource/topics/80-70017-254/how_to.html#use-ssh).
Note: If SSH is already enabled, you can skip this
                        step.
- Enter the SSH shell and run the use cases:

        ssh root@<ip-addr of the target device>Copy to clipboard
- Enable the
                    display:

        export XDG_RUNTIME_DIR=/dev/socket/weston && export WAYLAND_DISPLAY=wayland-1Copy to clipboard
- Push the files from the Linux
                    host:

        scp <filename> root@<IP address of target device>:/opt/Copy to clipboard
- Push the video.mp4 file in opt
                    folder.

## Run the application

For model and label files, see [Sample model and label files](https://docs.qualcomm.com/doc/80-70017-50/topic/ai-smart-codec.html#ai-smart-codec__section_lb3_1th_4dc).

- Run the application with a camera
                    source:

        gst-ai-smartcodec-example -w 1920 -h 1080 -o output.mp4 -m /opt/YOLOv8-Detection-Quantized.tflite -l /opt/coco_labels.txtCopy to clipboard
- Run the application with a file
                    source:

        gst-ai-smartcodec-example -i /opt/video.mp4 -o output.mp4 -m /opt/YOLOv8-Detection-Quantized.tflite -l /opt/coco_labels.txtCopy to clipboard

To display the available help options, run the following commands in the SSH
                shell:

    gst-ai-smartcodec-example --helpCopy to clipboard

To stop the use case, press CTRL + C.

## Expected output

The application generates the output as an encoded MP4 file.

## 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> |

**Parent Topic:** [AI/ML sample applications](https://docs.qualcomm.com/doc/80-70017-50/topic/ai-ml-sample-applications.html)

**Related Resources**  

- [Smart codec](https://docs.qualcomm.com/doc/80-70017-50/topic/smart-codec.html)

Last Published: Oct 01, 2026

[Previous Topic
Multistream batch inference](https://docs.qualcomm.com/bundle/publicresource/80-70017-50/topics/multistream-batch-inference.md) [Next Topic
Face detection](https://docs.qualcomm.com/bundle/publicresource/80-70017-50/topics/gst-ai-face-detection.md)