Oral microbiota can alter cancer susceptibility and progression by modulating metabolism and inflammation. We assessed the association between the oral microbiome and lymph node (LN) metastasis in oral squamous cell carcinoma (OSCC). We collected a total of 54 saliva samples from patients with OSCC before surgery. LN metastasis was assessed based on postoperative pathological examination. We used QIIME2, linear discriminant analysis effect size (LEfSe), and PICRUSt2 methods to analyze microbial dysbiosis. A random forest classifier was used to assess whether the oral microbiome could predict LN metastasis. Among the 54 OSCC samples, 20 had LN metastasis, and 34 had no evidence of metastasis. There was a significant difference in β-diversity between the metastasis and no metastasis groups. Through LEfSe analysis, the metastasis group was enriched in the genera Prevotella, Stomatobaculum, Bifidobacterium, Peptostreptococcaceae, Shuttleworthia and Finegoldia. Pathways related to signal peptidase II were predominant in the no metastasis group. The RF model showed a modestly high accuracy for predicting metastasis. Differences in microbial community composition and functions were observed in the oral microbiome of patients with OSCC with and without LN metastasis. However, the finding that specific taxa may be associated with LN metastasis should be verified in a further prospective study.