Abstract Introduction: Severe mental illnesses in young people (0–25 years) are often preceded by subtle changes in communication and thinking, detectable in speech and language. Speech and language markers are promising for early detection; however, no systematic review has evaluated their prospective utility in predicting mental health disorders in youth. We systematically reviewed longitudinal studies assessing speech and language markers as predictors of major mental health disorder onset or symptom progression in youth. Methods: We searched for longitudinal studies using recorded speech samples to predict diagnostic changes or symptom severity in major depressive disorder (MDD), psychosis, ADHD, substance use disorder, bipolar disorder, OCD, and eating disorders. Risk of bias was assessed using the Newcastle Ottawa Scale. Our protocol was pre-registered [CRD42024579798]. Results: Of 2,259 articles, 10 studies met inclusion criteria, covering MDD (n=2), psychosis (n=5), and ADHD (n=3). No eligible studies were found for OCD, substance use, bipolar, or eating disorders. Both manual and computational speech analyses were used, with speech samples from parents and youth. Predictive speech markers included parental expressed emotion (MDD, ADHD), formal thought disorder (psychosis), and acoustic/linguistic features (psychosis, ADHD). Study quality was moderate to good (mean score: 5.5/8). Conclusions: Externally validated longitudinal studies on the predictive value of speech and language markers of youth-onset mental disorders are scarce and restricted to a few target disorders. Nonetheless, existing studies highlight the potential of applying Natural Language Processing methods to speech samples from both youth and parents for early identification. Keywords: prediction; speech; youth mental health