ezlocalai

ezlocalai copied to clipboard

Added `create_audiobook` function. - API Endpoint added for `POST /v1/audio/book` - Accepts file upload - Accepts `voice` and `language` (2 letter) in the body optionally. Will use default voice and...

Josh-XT

Documenting how to add more models

2

Hi, great project! I'm wondering how one can add more models. I'm thinking of e.g STT and TTS using CoquiAI or Whisper.cpp. How do you recommend I do so rather...

Utopiah

Bumps [torch](https://github.com/pytorch/pytorch) from 2.3.1 to 2.6.0. Release notes Sourced from torch's releases. PyTorch 2.6.0 Release Highlights Tracked Regressions Backwards Incompatible Change Deprecations New Features Improvements Bug fixes Performance Documentation Developers...

dependabot[bot]

Potential fix for [https://github.com/DevXT-LLC/ezlocalai/security/code-scanning/5](https://github.com/DevXT-LLC/ezlocalai/security/code-scanning/5) To fix the problem, we need to ensure that the `audio_url` is validated before being used in the `requests.get` call. One way to do this is...

Josh-XT

Add Environment Variables to Disable Model Functionalities

9

Introduce environment variables to disable the loading of various model functionalities in ezLocalai. The specific functionalities to be optionally disabled via environment variables include the LLM, vision model, image generation...

Josh-XT