Update README.md

README.md

@@ -122,7 +122,8 @@ Instead of slow diffusion decoders, Soprano uses a **Vocos‑based decoder**, en
 
 ### 3. Seamless real‑time streaming
 
-A novel streaming strategy leverages the decoder’s receptive field to generate audio with **ultra‑low latency**. The streamed output is acoustically identical to offline synthesis, enabling interactive applications with sub‑frame delays.
+
+Soprano leverages the decoder’s finite receptive field to losslessly stream audio with **ultra‑low latency**. The streamed output is acoustically identical to offline synthesis, enabling interactive applications with sub‑frame delays.
 
 ### 4. State‑of‑the‑art neural audio codec