draft: audiobook

README.md

@@ -50,7 +50,7 @@ pip install -r requirements.txt
 
 </details>
 
-Start Flask
+Flask API
 
 ```
 CUDA_DEVICE_ORDER=PCI_BUS_ID HF_HOME=./hf_home CUDA_VISIBLE_DEVICES=2 python api.py
@@ -96,7 +96,7 @@ For SHIFT demo / Collaboration with [SMB](https://www.smb.museum/home/)
 
 # Live Demo - Paplay
 
-Flask
+Special Flask API for playing sounds live
 
 ```python
 CUDA_DEVICE_ORDER=PCI_BUS_ID HF_HOME=/data/dkounadis/.hf7/ CUDA_VISIBLE_DEVICES=4 python live_api.py
@@ -113,3 +113,17 @@ python live_demo.py  # will ask text input & play soundscape
 ```python
 CUDA_DEVICE_ORDER=PCI_BUS_ID HF_HOME=/data/dkounadis/.hf7/ CUDA_VISIBLE_DEVICES=4 python demo.py
 ```
+
+# AudioBook
+
+Convert your `.docx` to audio `.wav`. Via multiple voices, then concatenate all `audiobooks.wav` made with each voice to a full one
+`concatenate audiobook has noisy speech, the individual single-voice audiobooks are clean, some issue with ffmpeg`. Therefore, for now, SHIFT repo only produces 
+single-voice audiobook. Archiving the multiple-voice `audiobook.py` here.
+
+```python
+# uses Flask api.py
+# needs to load ../shift/assets/INCLUSION_IN_MUSEUMS_audiobook.docx
+#
+# 
+python audiobook.py 
+```