Play the clip inline in a notebook, and say what Colab needs

README.md

@@ -145,10 +145,20 @@ with torch.inference_mode():
     speech = model.generate_speech(ids, speaker, vocoder=vocoder)
 
 sf.write("out.wav", speech.numpy(), 16000)   # 16 kHz mono
+
+# In a notebook (Colab, Jupyter), play it inline instead of saving:
+from IPython.display import Audio, display
+display(Audio(speech.numpy(), rate=16000))
 ```
 
-Runs on CPU. For GPU, `.to("cuda")` the model, the vocoder and `ids`/`speaker`,
-then `.cpu()` the result before `sf.write`.
+Runs unmodified on a stock Colab CPU runtime — every dependency is preinstalled,
+including the `sentencepiece` the tokenizer needs — at roughly 1.8× real time.
+For GPU, `.to("cuda")` the model, the vocoder and `ids`/`speaker`, then `.cpu()`
+the result before `sf.write`.
+
+The `display(Audio(...))` line renders a play button in a notebook cell. It
+produces no sound over a terminal or SSH session; there, write the wav and fetch
+it (`from google.colab import files; files.download("out.wav")`).
 
 Spell numbers out: the tokenizer is character-level Latin and drops digits
 silently.