Voice LLM Application - Experiment 05: Multimodal Document Analysis - Voice Dialogue

Experiment Preparation:

  1. Ensure Doubao AI (Volcengine) and iFlytek AI are connected (refer to Experiment 01, Experiment 02)
  2. Find documents as experiment material. Document import can be relative or absolute path. Relative path defaults to AI_online_voice/assets/text.docx
  3. Download related dependencies (skip if already installed)
  • pip install python-docx
  • pip install openpyxl

Experiment Steps: (Ensure voice module is connected)

  1. cd AI_online_voice # Enter main directory
  2. python examples/05_voice_document_analysis.py # Run example program
  3. After entering the program, according to terminal prompts, first enter y to enter document selection. Can choose absolute or relative path.

Terminal Operation Example:

TOOLTOOL

Experiment Effect: Document upload → Multimodal LLM document analysis → Voice dialogue output, implementing document understanding and voice interaction