To substitute fossil fuels, biodiesel can be produced from vegetable oils, animal fats, and waste cooking oils by transesterification with ethanol. Various factors such as free fatty acid content, water content, type/amount of catalyst, vegetable oil to alcohol molar ratio, or temperature can affect this process. Many analytical procedures using gas chromatography and high performance liquid chromatography have been developed to determine the composition of crude transesterification products but these techniques are long to handle, unreliable and expensive methods of on-line monitoring. In this work, an innovative method using NIR spectroscopy to on-line monitor the transesterification reaction of high oleic sunflower oil with ethanol in a one-liter-batch reactor was developed. Partial least squares regression was used to develop calibration models between NIR spectral data and analytical data obtained by a reference method: gas chromatography with flame ionization detection (GC-FID). The results indicated that the use of NIR spectroscopy is an appropriate technique to research optimal reaction parameters and obtain kinetic data for a range of temperature from 30°C to 80°C. It was also shown that the water content in ethanol or oil has a negative influence on ethyl ester production.