The temporal relationship between sentence-level intonation planning and word-level phonological encoding remains poorly understood. Prosody-first accounts predict that an abstract intonation frame is established before lexical information is retrieved, whereas prosody-last accounts predict that intonation is encoded after lexical information. The present study used EEG combined with time-resolved multivariate pattern analysis (MVPA) to investigate when intonation planning occurs relative to other levels of linguistic encoding during spoken word production. Thirty native Dutch speakers named pictures of simple nouns using two different intonation contours, as either questions or exclamations. The target words were disyllabic Dutch nouns that varied in animacy, lexical stress, and manner and place of articulation of the first phoneme. Intonation became decodable after animacy and around the same time as place of articulation. Exploratory analyses revealed that intonation decoding emerged earlier for words with word-final than word-initial stress, suggesting that the temporal profile of intonation planning is shaped by the word’s stress pattern. On a methodological level, these findings demonstrate that intonation planning is neurally decodable in an overt production context using EEG. The implications for theories of language production are that sentence-level and word-level prosody closely interact and evolve together during planning rather than being encoded independently.