Population approaches to lessen the adverse impacts of preschool language delay remain elusive. We aimed to determine whether systematic ascertainment of language delay at age 4 years, followed by a 10-month, 1-on-1 intervention, improves language and related outcomes at age 5 years. A randomized trial nested within a cross-sectional ascertainment of language delay. Children with expressive and/or receptive language scores more than 1.25 SD below the mean at age 4 years entered the trial. Children randomly allocated to the intervention received 18 1-hour home-based therapy sessions. The primary outcomes were receptive and expressive language (Clinical Evaluation of Language Fundamentals - Preschool, 2(nd) Edition) and secondary outcomes were child phonological skills, letter awareness, pragmatic skills, behavior, and quality of life. A total of 1464 children were assessed for language delay at age 4 years. Of 266 eligible children, 200 (13.6%) entered the trial, with 91 intervention (92% of 99) and 88 control (87% of 101) children retained at age 5 years. At age 5 years, there was weak evidence of benefit to expressive (adjusted mean difference, intervention - control, 2.0; 95% confidence interval CI -0.5 to 4.4; P = .12) but not receptive (0.6; 95% CI -2.5 to 3.8; P = .69) language. The intervention improved phonological awareness skills (5.0; 95% CI 2.2 to 7.8; P < .001) and letter knowledge (2.4; 95% CI 0.3 to 4.5; P = .03), but not other secondary outcomes. A standardized yet flexible 18-session language intervention was successfully delivered by non-specialist staff, found to be acceptable and feasible, and has the potential to improve long-term consequences of early language delay within a public health framework.