Update README.md

README.md

@@ -13,7 +13,9 @@ language:
   - ar
   - hi
   - sw
-license: mit
+license: other
+license_name: ltx-2-community
+license_link: https://github.com/Lightricks/LTX-2/blob/main/LICENSE
 tags:
   - audio-generation
   - diffusion
@@ -22,6 +24,7 @@ tags:
   - speech-generation
   - expressive-speech
   - voice-acting
+  - text-to-speech
 pipeline_tag: text-to-speech
 library_name: scenema-audio
 inference: false
@@ -253,6 +256,8 @@ Benchmarked on NVIDIA RTX 4090 (24 GB), ~55 seconds of output audio:
 
 ## License
 
-MIT License. See [LICENSE](LICENSE) for details.
+The model weights are released under the [LTX-2 Community License Agreement](https://github.com/Lightricks/LTX-2/blob/main/LICENSE). Scenema Audio's audio diffusion transformer is derived from [LTX 2.3](https://github.com/Lightricks/LTX-2)'s audiovisual model, and its weights are subject to the same terms.
 
-Gemma 3 12B (text encoder) is a gated model requiring Google's terms of use.
+The inference code and server are released under the [MIT License](https://github.com/ScenemaAI/scenema-audio/blob/main/LICENSE).
+
+[Gemma 3 12B](https://ai.google.dev/gemma/terms) (text encoder) is a gated model requiring acceptance of Google's terms of use.