This study investigates the feasibility to predict individual methane (CH4) emissions from dairy cows using milk mid-infrared (MIR) spectra. To have a large variability of milk composition, two experiments were conducted on 11 lactating Holstein cows (two primiparous and nine multiparous). The first experiment aimed to induce a large variation in CH4 emission by feeding two different diets: the first one was mainly composed of fresh grass and sugar beet pulp and the second one of maize silage and hay. The second experiment consisted of grass and corn silage with cracked corn, soybean meal and dried pulp. For each milking period, the milk yields were recorded twice daily and a milk sample of 50 ml was collected from each cow and analyzed by MIR spectrometry. Individual CH4 emissions were measured daily using the sulfur hexafluoride method during a 7-day period. CH4 daily emissions ranged from 10.2 to 47.1 g CH4/kg of milk. The spectral data were transformed to represent an average daily milk spectrum (AMS), which was related to the recorded daily CH4 data. By assuming a delay before the production of fermentation products in the rumen and their use to produce milk components, five different calculations were used: AMS at days 0, 0.5, 1, 1.5 and 2 compared with the CH4 measurement. The equations were built using Partial Least Squares regression. From the calculated R2cv, it appears that the accuracy of CH4 prediction by MIR changed in function of the milking days. In our experimental conditions, the AMS at day 1.5 compared with the measure of CH4 emissions gave the best results. The R2 and s.e. of the cross-validation were equal to 0.79 and 5.14 g of CH4/kg of milk. The multiple correlation analysis performed in this study showed the existence of a close relationship between milk fatty acid (FA) profile and CH4 emission at day 1.5. The lower R2 (R2 = 0.76) obtained between FA profile and CH4 emission compared with the one corresponding to the obtained calibration (R2c = 0.87) shows the interest to apply directly the developed CH4 equation instead of the use of correlations between FA and CH4. In conclusion, our preliminary results suggest the feasibility of direct CH4 prediction from milk MIR spectra. Additional research has the potential to improve the calibrations even further. This alternative method could be useful to predict the individual CH4 emissions at farm level or at the regional scale and it also could be used to identify low-CH4-emitting cows.