Built-in edge speech api for text-to-speech

[AndrewHan0457]

Seems sadtalker has no text to audio feature, I try to use edge speech api to make it.

SadTalker with Edge Speech api (edge-tts): sad_talker-git.zip

1. download the zip package and uncompress.
2. relplace app_sadtalker.py file under root path with the same name file in uncompressed dir And add t2a.py file under <root>/src/
   (Suppose you have configured the sadtalker runtime environment)
3. run the sadtalker you will get: (mine with zh pkg)
   
   with the Edge Speech api, you can choose voice, rate, volume to generate audio from text:
   

[Jackzxs]

I follow you step to replace app_sadtalker.py and add t2a.py file ,but I run wubui.bat file , some error is occure:

venv "venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash:
Installing requirements for SadTalker WebUI (may take longer time in first time)
Launching SadTalker Web UI
Traceback (most recent call last):
File "D:\reposity\SadTalker-main\app_sadtalker.py", line 80, in sadtalker_demo
driven_audio = gr.Audio(value="./audio/tmp.mp3", label="Input audio", source="upload", type="filepath")
File "D:\reposity\SadTalker-main\venv\lib\site-packages\gradio\components\audio.py", line 127, in init
IOComponent.init(
File "D:\reposity\SadTalker-main\venv\lib\site-packages\gradio\components\base.py", line 182, in init
else self.postprocess(initial_value)
File "D:\reposity\SadTalker-main\venv\lib\site-packages\gradio\components\audio.py", line 359, in postprocess
file_path = self.make_temp_copy_if_needed(y)
File "D:\reposity\SadTalker-main\venv\lib\site-packages\gradio\components\base.py", line 226, in make_temp_copy_if_needed
temp_dir = self.hash_file(file_path)
File "D:\reposity\SadTalker-main\venv\lib\site-packages\gradio\components\base.py", line 190, in hash_file
with open(file_path, "rb") as f:
FileNotFoundError: [Errno 2] No such file or directory: './audio/tmp.mp3'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:\reposity\SadTalker-main\Launcher.py", line 204, in
start()
File "D:\reposity\SadTalker-main\Launcher.py", line 198, in start
demo = sadtalker_demo()
File "D:\reposity\SadTalker-main\app_sadtalker.py", line 32, in sadtalker_demo
with gr.Blocks(analytics_enabled=False) as sadtalker_interface:
File "D:\reposity\SadTalker-main\venv\lib\site-packages\gradio\blocks.py", line 1526, in exit
self.config = self.get_config_file()
File "D:\reposity\SadTalker-main\venv\lib\site-packages\gradio\blocks.py", line 1493, in get_config_file
props = block.get_config() if hasattr(block, "get_config") else {}
File "D:\reposity\SadTalker-main\venv\lib\site-packages\gradio\components\audio.py", line 147, in get_config
"value": self.value,
AttributeError: 'Audio' object has no attribute 'value'

Is other configuration need to set it？

[AndrewHan0457]

sry I forgot to add tmp audio file, the error msg means there's no /audio/tmp.mp3 file, you can fix it by:
1, create a new folder under D:\reposity\SadTalker-main named audio and find one any .mp3 file renamed to tmp.mp3.
2, add the tmp.mp3 file under D:\reposity\SadTalker-main\audio
now you can run sadtalker