kromskii2/alltalk_tts
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
erew123 authored and GitHub committed 2023-12-08 17:24:36 +00:00
1 parent 5692fc1777
commit b15bf181b4
1 file changed
+8 -8
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+8 -8
View File
@@ -1,14 +1,14 @@
# AllTalk TTS # AllTalk TTS
AllTalk is an updated version of the Coqui_tts extension for Text Generation web UI. Features include: AllTalk is an updated version of the Coqui_tts extension for Text Generation web UI. Features include:
- Settings page to adjust your base startup settings. - **Default Settings:** Adjust your standard startup settings.
- Low VRAM mode to improve performance where your LLM takes up your VRAM. - **Low VRAM mode:** Improve generation performance if your VRAM is filled by your LLM.
- DeepSpeed voice processing, giving a 3-4x performance boost (requires DeepSpeed installing). - **DeepSpeed:** When DeepSpeed is installed you can get a 3-4x performance boost generating TTS.
- Local/Custom models (API Local and XTTSv2 Local). - **Local/Custom models:** Use any of the XTTSv2 models (API Local and XTTSv2 Local).
- Configurable deletion of old wav file outputs. - **Wav file maintenance:** Configurable deletion of old output wav files.
- Built in manual & settings on a web page. - **Documentation:** Fully documented with a built in webpage.
- Clear command line output for any warnings or issues. - **Console output** Clear command line output for any warnings or issues.
- Can be used with 3rd party applications via JSON calls. - **3rd Party support via JSON calls** Can be used with 3rd party applications via JSON calls.
**Mac compatibility is not yet guaranteed due to CUDA requirement** **Mac compatibility is not yet guaranteed due to CUDA requirement**