From 26c1f17ee12991279a082c77b9e7fb8727d3fe10 Mon Sep 17 00:00:00 2001 From: fbdp1202 Date: Fri, 15 May 2026 23:35:33 +0900 Subject: [PATCH] docs: annotate Quick Start with wav/duration shapes and soundfile alternative Co-Authored-By: Claude Opus 4.7 (1M context) --- README.md | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/README.md b/README.md index 78bb674..0fc05b6 100644 --- a/README.md +++ b/README.md @@ -73,8 +73,13 @@ wav, duration = tts.synthesize( total_steps=8, # Quality: 5 (low) to 12 (high), default 8 (medium) speed=1.05, # Speed: 0.7 (slow) to 2.0 (fast) ) +# wav: numpy array of shape (1, num_samples,) with dtype=np.float32, sampled at 44100 Hz +# duration: numpy array of shape (1,) containing the duration of the generated audio in seconds tts.save_audio(wav, "output.wav") +# import soundfile as sf +# sf.write("output.wav", wav.squeeze(), 44100) + print(f"Generated {duration[0]:.2f}s of audio") ```