The responsivity of an ultrasonic transducer is an important parameter in evaluating its effective frequency band, the electroacoustic conversion efficiency, and the measurement capability of the system. The determination of the responsivity of a traditional immersion or contact piezoelectric transducer has been well investigated. However, due to the high attenuation of waves propagating in air and the large acoustic impedance mismatch between the active piezoceramic material and the load medium, there are few reports of the calibration of an air-coupled piezoelectric transducer. In this work, we present a comparative method of measuring the responsivity of an air-coupled transducer: the air-coupled transducer is used to receive a broadband pulse signal to evaluate its frequency spectrum, and a toneburst signal with known vibration displacement is measured by the air-coupled transducer in order to calibrate the amplitude of the responsivity. The effects of transmitter responsivity, input pulse characteristics, attenuation, and diffraction are taken into account to improve the accuracy of the responsivity determination. In addition, the measurement of the amplitude of the responsivity by comparing the measured displacements avoids the complicated task of characterizing the effects of electrical equipment. The determined responsivity is checked by comparing the measured displacements using different methods at different frequencies in order to evaluate its frequency spectrum and by measuring the nonlinearity parameters of the material to evaluate its amplitude. The agreement between results obtained using different methods demonstrates that the calibrated responsivity of the air-coupled transducer is valid, and the proposed method is effective.