diff --git a/README.md b/README.md
index e82d8ca..ff964b2 100755
--- a/README.md
+++ b/README.md
@@ -42,7 +42,7 @@ With compact __custom pre-trained transformer models__, this can run anywhere fr
 
 ## Features
 
-- __Tiny Embeddings__: 64-dimensional [Matryoshaka][matryoshka]-style embeddings for extremely fast [search][usearch].
+- __Tiny Embeddings__: 64-dimensional [Matryoshka][matryoshka]-style embeddings for extremely fast [search][usearch].
 - __Throughput__: Thanks to the small size, the inference speed is [2-4x faster](#speed) than competitors.
 - __Portable__: Models come with native ONNX support, making them easy to deploy on any platform.
 - __Quantization Aware__: Down-cast embeddings from `f32` to `i8` without losing much recall.