Skip to main content

Input

  • Required Inputs:
    • output: URL of the audio recording to evaluate

Output

  • Result: One of positive, negative, or neutral
  • Reasoning: Brief explanation for the classification
Supported models: Gemini 2.5 Flash (recommended), GPT-4o Audio Preview, Gemini 2.5 Pro. Gemini 2.5 Flash is recommended for best performance and latency.

Interpretation

  • positive: Predominantly positive affect (e.g., satisfied, pleased)
  • negative: Predominantly negative affect (e.g., angry, frustrated)
  • neutral: Largely neutral, very casual without any emotions shown