Cryptococcal meningitis (CM) causes 10-20% of HIV-related deaths in Africa. We performed a phase-II non-inferiority trial examining the Early Fungicidal Activity (EFA) of three short-course, high-dose liposomal amphotericin B (L-AmB) regimens for CM in Tanzania and Botswana. HIV-infected adults with CM were randomized to: (i) L-AmB 10mg/kg day 1 (single dose); (ii) L-AmB 10mg/kg day 1, 5mg/kg day 3 (two doses); (iii) L-AmB 10mg/kg day 1, 5 mg/kg days 3 and 7 (three doses); (iv) standard 14-day L-AmB 3mg/kg/day (control); all given with fluconazole 1200mg/day for 14 days. Primary endpoint was mean rate of clearance of cerebrospinal fluid (CSF) cryptococal infection (EFA). Non-inferiority was defined as an upper limit of the two-sided 95% confidence interval (CI) of difference in EFA between intervention and control less than 0.2 log10CFU/ml/day. 80 participants were enrolled. EFA for daily L-AmB was -0.41 (standard deviation 0.11, n=17) log10CFU/mL/day. Difference in mean EFA from control was -0.11 (95%CI -0.29,0.07) log10CFU/mL/day faster with single dose (n=16); -0.05 (95%CI -0.20,0.10) log10CFU/mL/day faster with two doses (n=18); and -0.13 (95%CI -0.35,0.09) log10CFU/mL/day faster with three doses (n=18). EFA in all short-course arms was non-inferior to control at the predefined non-inferiority margin. Overall 10-week mortality was 29% (n=23) with no statistical difference between arms. All arms were well tolerated. Single dose 10mg/kg L-AmB was well tolerated and led to non-inferior EFA compared to 14 days of 3mg/kg/d L-AmB in HIV-associated CM. Induction based on single 10mg/kg L-AmB dose is being taken forward to a phase-III clinical endpoint trial.