diff --git a/README.md b/README.md
index 29ec19a..a994e88 100644
--- a/README.md
+++ b/README.md
@@ -144,6 +144,7 @@ Output defaults to `input.<target_code>.srt` (e.g., `input.deu_latn.srt`).
     
 -   **Ollama engine errors:** Confirm `ollama serve` or the desktop app is running and the model tag exists locally (`ollama list` / `ollama pull <model>`).
     
--   **Large downloads:** The first run will download large AI models (NLLB can be a bit slower; subsequent runs are cached.
+-   **Large downloads:** The first run will download large AI models (NLLB around 2.5GB, SeamlessM4T around 10GB, Ollama model depending on your choice).
+