AllTalk is based on the Coqui TTS engine, similar to the Coqui_tts extension for Text generation webUI, however supports a variety of advanced features, such as a settings page, low VRAM support, DeepSpeed, narrator, model finetuning, custom models, wav file maintenance. It can also be used with 3rd Party software via JSON calls.
Looks like pytorch index URLs got truncated: https://github.com/erew123/alltalk_tts/blob/fff01107c89cea9e7f0405e247da0f39637dc957/atsetup.sh#L328
It should still point to
https://download.pytorch.org/whl/cu121
, I think.