| 12345678910111213141516171819202122232425262728293031 |
- name: empiriolabs-media
- title: EmpirioLabs AI Media
- repo: https://github.com/EmpirioLabs-AI/hermes-empiriolabs
- sha: 20f049d5913ec850e98bef3d289f6cb43645869e
- subdir: media
- description: >-
- EmpirioLabs AI backends for Hermes' image_generate, video_generate and text_to_speech tools
- (backend `empiriolabs` for image_gen.provider, video_gen.provider and tts.provider): image
- generation and editing, text-to-video and image-to-video, and text-to-speech, with models and
- voices from the live EmpirioLabs AI catalog. Submitted by EmpirioLabs AI. Disclosure: registers
- three backends and nothing else (no tools, hooks, commands or threads); when one is selected and
- its tool is called, the prompt, source images or text to speak go to
- https://api.empiriolabs.ai/v1 (or EMPIRIOLABS_BASE_URL) with EMPIRIOLABS_API_KEY, read through
- Hermes' secret scope, and each call is billed to that EmpirioLabs AI account with no Hermes
- approval prompt; it reads the model catalog (GET /v1/models), polls GET /v1/jobs/{id} while a
- generation runs (videos up to 15 minutes by default), downloads the generated files from the
- returned URLs into Hermes' cache (the key is never sent to them), and reads a local image file
- only when the agent asks to edit one.
- maintainer: EmpirioLabs-AI
- tier: community
- category: tools
- requires_hermes: ">=0.21.6"
- version: "1.0.0"
- docs_url: https://github.com/EmpirioLabs-AI/hermes-empiriolabs/blob/20f049d5913ec850e98bef3d289f6cb43645869e/media/README.md
- platforms: []
- capabilities:
- provides_tools: []
- provides_hooks: []
- provides_middleware: []
- requires_env:
- - EMPIRIOLABS_API_KEY
|