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
871 stars 100 forks source link

Bark Integration #333

Closed nicoan777 closed 1 week ago

nicoan777 commented 1 week ago

Just as the title. Surprised that is not here: https://github.com/suno-ai/bark

erew123 commented 1 week ago

Hi @nicoan777

Bark is part of the Coqui suite, so in theory it wouldn't be too complicated to change the existing XTTS engine setup https://github.com/erew123/alltalk_tts/tree/alltalkbeta/system/tts_engines/xtts

Using the template information/guide https://github.com/erew123/alltalk_tts/tree/alltalkbeta/system/tts_engines/template-tts-engine

to change the XTTS engine to use the Bark configuration https://docs.coqui.ai/en/latest/models/bark.html

If you have a little coding experience, you are welcome to give it a shot, it shouldn't be too complicated considering its just a variant on XTTS.

I however have limited time currently, due to having to care for a family member, and dealing with a backlog of support requests. However, I have some in-progress work adding additional TTS engines and did intend to add all other Coqui variants in time.

Thanks