Attenuated total reflectance mid infrared (ATR-MIR) spectroscopy is a potential technique for the near real-time monitoring of filamentous bioprocesses. Here we investigate the utility of ATR-MIR to monitor and predict concentrations of glycerol and product (clavulanic acid) in a complex antibiotic bioprocess. Streptomyces clavuligerus exhibits filamentous growth, thus, as biomass accumulates the process fluid becomes much more viscous, and develops pronounced non-Newtonian behaviour. A multivariate statistical technique, partial least square (PLS) has been used to develop models for the key analytes over the time course of the bioprocess. These models were then validated externally using unseen samples, not used in the original modelling exercise. Despite the heterogeneous nature of the bioprocess and the resulting complexity of the spectra, the models developed had high correlation coefficient values and low prediction error values of 0.302 and 0.009 for glycerol and clavulanic acid, respectively. The findings extend the use of ATR-MIR in these difficult fluids which are typical of filamentous industrial bioprocesses, and demonstrate the practical utility of the technique in the measurement of a range of analyte types, including those present at relatively modest levels compared to the concentrations of biomass and major substrates.