Playing music over the Internet, whether for real-time jamming, network performance or distance education, is constrained by the speed of light which introduces, over long distances, time delays unsuitable for musical applications. Current musical collaboration systems generally transmit compressed audio streams over low-latency and high-bandwidthnetworks to optimize musician synchronization. This paperproposes an alternative approach based on pattern recognition and music prediction. Trained for a particular typeof music, here the Indian tabla drum, the system calledTablaNet identifies rhythmic patterns by recognizing individual strokes played by a musician and mapping them dynamically to known musical constructs. Symbols representing these musical structures are sent over the network toa corresponding computer system. The computer at thereceiving end anticipates incoming events by analyzing previous phrases and synthesizes an estimated audio output.Although such a system may introduce variants due to prediction approximations, resulting in a slightly different musical experience at both ends, we find that it demonstratesa high level of playability with an immediacy not present inother systems, and functions well as an educational tool.