Phyto-oestrogens have been suggested to have a protective effect on hormone-sensitive cancers. However, few studies have investigated the association between dietary phyto-oestrogens and gynaecological cancers. In the present study, we analysed data from two population-based case–control studies of ovarian (1366 cases and 1414 controls) and endometrial (1288 cases and 1435 controls) cancers. Dietary intake information was obtained using a 135-item FFQ, and phyto-oestrogen intake was estimated using published food composition databases. Unconditional logistic regression was used to estimate adjusted OR and 95 % CI. In multivariable analyses, there was a suggestive pattern of inverse associations between increasing intakes of total phyto-oestrogens, isoflavones and enterolignans and the risk of ovarian cancer. However, the results only reached statistical significance for the lignan compounds matairesinol and lariciresinol, where the OR for the highest v. the lowest intake category was 0·72 (95 % CI 0·54, 0·96; P for trend = 0·02) for matairesinol and 0·72 (95 % CI 0·55, 0·96; P for trend = 0·03) for lariciresinol. When the risk of ovarian cancer was assessed by subtype, there was an indication that increasing intakes of phyto-oestrogens may be associated with a decreased risk of mucinous (cases n 158) ovarian tumours (OR for the highest v. the lowest intake category: 0·47 (95 % CI 0·24, 0·93); P for trend = 0·04). However, there were no significant associations with other histological subtypes. In contrast, dietary phyto-oestrogens (total or any subclass) were unrelated to the risk of endometrial cancer cases overall or by subtype.