• Evaluate AI-generated speech for naturalness, human likeness, and expressiveness, identifying areas for improvement. • Analyze conversational audio to accurately segment and label individual speakers. • Compare AI and human responses to assess fluency, coherence, and realism. • Assess synthetic speech by detecting errors in pronunciation, rhythm, and intonation. • Provide structured feedback to enhance AI model accuracy and performance. • Maintain high attention to detail and follow evaluation guidelines consistently. • Must be able to receive and implement quality feedback from the project team