2023-12-09 19:18:05 +00:00
2023-12-09 19:14:54 +00:00
2023-12-08 09:35:53 +00:00
2023-12-08 09:35:19 +00:00
2023-12-09 19:14:54 +00:00
2023-12-08 09:35:53 +00:00
2023-12-08 09:35:53 +00:00
2023-12-08 09:35:53 +00:00
2023-12-08 14:54:45 +00:00
2023-12-08 17:31:12 +00:00
2023-12-09 19:18:05 +00:00
2023-12-09 19:14:54 +00:00
2023-12-08 09:35:53 +00:00
2023-12-09 19:14:54 +00:00

AllTalk TTS

AllTalk is an updated version of the Coqui_tts extension for Text Generation web UI. Features include:

  • Default Settings: Adjust your standard startup settings.
  • Low VRAM mode: Improve generation performance if your VRAM is filled by your LLM.
  • DeepSpeed: When DeepSpeed is installed you can get a 3-4x performance boost generating TTS.
  • Local/Custom models: Use any of the XTTSv2 models (API Local and XTTSv2 Local).
  • Wav file maintenance: Configurable deletion of old output wav files.
  • Documentation: Fully documented with a built in webpage.
  • Console output Clear command line output for any warnings or issues.
  • 3rd Party support via JSON calls Can be used with 3rd party applications via JSON calls.

Note: Mac compatibility is not yet guaranteed due to CUDA requirement

Installation on Text generation web UI

In a command prompt/terminal window you need to move into your Text generation webUI folder e.g. cd text-generation-webui and then into your extensions folder e.g. cd extensions

Once there git clone this repository e.g.

git clone https://github.com/erew123/alltalk_tts

You can now start up Text generation web UI and activate AllTalk in your extensions. To start it every time when Text generation webUI loads, edit the CMD_FLAGS.txt file in the main text-generation-webui folder and add --extensions alltalk_tts

Main Page

image

Settings Page

image

S
Description
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,
Readme AGPL-3.0
94 MiB
0 Stars 1 Watchers 0 Forks
Languages
HTML 46.8%
Python 37.1%
JavaScript 9.9%
Batchfile 3%
Shell 2.4%
Other 0.8%