realnikolaj

Had the same problem. Reinstalling colima using `brew install --HEAD colima` did not fix the problem, but it's the version I used when the below fixed my issue. What fixed...

EDIT: Sorry I missed that you're probable dealing with the inpainting folder, but the reply here is general for any models/folder and worth a try. Are you running the local...

> I have the same problem of [@dgshue](https://github.com/dgshue) on Open WebUI logs: `open_webui.routers.audio:get_available_voices:1015 - Error fetching voices from custom endpoint: 404 Client Error: Not Found for url: http://speaches/v1/audio/voices` `open_webui.routers.audio:get_available_models:968 -...

Details > > The speaches docs have the API page where you can see which GET/POST methods are actually available and the ones Open-WebUI are currently not. > > You'll...

@TheDarkula see maybe #475 Try without "s" in https, unless you know you got certificates sorted out already. Then try and add env ALLOW_ORIGINS, `LOOPBACK_HOST_URL http://:` `ALLOW_ORIGINS ["*"]` Don't actually...

Did you try the older WebUI version?

Details I've found a way to get `speaches` working (I might try and make a PR if [@av](https://github.com/av) doesn't beat me to it): * Stop all `harbor` services, just to...

@NN708 Try this **STT_MODEL**: > ` Systran/faster-whisper-large-v2 ` The '_distill_'s and '_v3_' versions of faster-whisper doesn't support Chinese, but the v2 does.

Sorry my bad then, this is the TTS model I've had "success" with: > `speaches-ai/piper-zh_CN-huayan-x_low`

@Acly Appreciate your work and your quick reply. Yeah, I thought you already put some thoughts into this and I see where you're coming from. Maybe my issue is with...