search

erew123 / alltalk_tts

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.
GNU Affero General Public License v3.0
1.16k stars 123 forks source link

Multiple voices in generator #334

Closed ErnieV closed 2 months ago

ErnieV commented 2 months ago

Did you consider doing multiple voices in TTS Generator? You could let it read a whole book and do a different voice for all of the characters.

We’d need some kind of markup for each character like This is the narrator <\nar>

This is Harry Potter <\hp> And a way to link each markup to a voice. Just a thought. Love the thing as is tho!
erew123 commented 2 months ago

Hi @ErnieV

This has kind of been requested in the API suite already. Its in the Feature requests https://github.com/erew123/alltalk_tts/discussions/74

Its possible, as everything is in code, but quite complicated too and obviously a question of time to write something to handle it. So as/when/if I get time to do it, it will be there.

Thanks