Voice LLM Application - Experiment 04: Multimodal Image Comparison - Voice Dialogue

Experiment Preparation:

  1. Ensure Doubao AI (Volcengine) and iFlytek AI are connected (refer to Experiment 01, Experiment 02)
  2. Find images as experiment material. Image import can be relative or absolute path. Relative path defaults to AI_online_voice/assets/sample.jpg

Experiment Steps: (Ensure voice module is connected)

  1. cd AI_online_voice # Enter main directory
  2. python examples/04_voice_image_comparison.py # Run example program
  3. After entering the program, according to terminal prompts, first enter y to enter image selection. Can choose absolute or relative path for voice.

Terminal Operation Example:

Image setup:

TOOL

Image comparison analysis:

TOOL

Experiment Effect: Select two images → Multimodal LGM comparative analysis → Voice dialogue output, implementing image comparison understanding