gallery: correct the audio.cpp entries' licenses

Swept all ten entries against the real upstream named in audio.cpp's
tools/model_manager.py rather than against the audio.cpp repo's own license.
Three were wrong:

  supertonic   apache-2.0 -> openrail      weights come from
                                           mlx-community/supertonic-3-mlx, and
                                           both it and Supertone/supertonic are
                                           openrail
  citrinet     apache-2.0 -> other         pulled from NGC
                                           nvidia/nemo/stt_en_citrinet_256,
                                           governed by the NGC Terms of Use
  sortformer   other -> cc-by-nc-4.0       nvidia/diar_sortformer_4spk-v1 is
                                           CC BY-NC 4.0, and the gallery already
                                           uses that exact string, so there is no
                                           reason to obscure a non-commercial bar

The license field is one word, so citrinet and sortformer also gained a
sentence saying why they are restricted. The other seven were confirmed
correct against their sources.

Also drops an unverified claim from the nemotron description. It said the
model drives the realtime transcription session; that endpoint actually calls
TranscribeStream, and the live RPC reaches LocalAI only through
realtime_semantic_vad.go. Neither path was exercised here, so the description
now states only the two calls that were.

MarbleNet gains the NeMo upstream under urls: for parity with silero.

No sha256, quantization, usecase or model choice changed.

Assisted-by: Claude:claude-opus-5 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

gallery/index.yaml

@@ -46737,7 +46737,7 @@
     process inside ggml_concat when tested locally. The backend refuses
     anything but f32/i64 weights for this family, so a wrong build fails at
     load with a clear message rather than crashing.
-  license: apache-2.0
+  license: openrail
   tags:
     - audio-cpp
     - supertonic
@@ -46807,7 +46807,11 @@
     the audio-cpp backend through /v1/audio/transcriptions. 40 MB, offline
     transcription only. Q8_0 is the only package upstream publishes and tests
     for this family, and it is recorded as a clean Pass.
-  license: apache-2.0
+
+    Licensing: the checkpoint is pulled from NVIDIA NGC
+    (nvidia/nemo/stt_en_citrinet_256), whose use is governed by the NGC Terms
+    of Use rather than a named open licence.
+  license: other
   tags:
     - audio-cpp
     - citrinet
@@ -46836,9 +46840,9 @@
     - https://github.com/0xShug0/audio.cpp
   description: |
     Nemotron 3.5 ASR Streaming 0.6B (audio.cpp, F16) - streaming English speech
-    to text, served by the audio-cpp backend. This is the family behind the
-    live transcription RPC, so it drives the realtime transcription session as
-    well as ordinary /v1/audio/transcriptions calls.
+    to text, served by the audio-cpp backend. It serves the backend's live
+    bidirectional transcription RPC as well as ordinary
+    /v1/audio/transcriptions calls.
 
     F16 rather than Q8_0 because upstream's tested-status table records Q8_0 as
     "Pass (minor filler drift)" while 16-bit is a clean Pass, and drift in a
@@ -46878,7 +46882,10 @@
 
     Q8_0 because upstream records it as a clean Pass, the same as 16-bit, at
     two thirds of the size.
-  license: other
+
+    Licensing: the base checkpoint nvidia/diar_sortformer_4spk-v1 is
+    CC BY-NC 4.0, so commercial use is not permitted.
+  license: cc-by-nc-4.0
   tags:
     - audio-cpp
     - sortformer
@@ -47043,6 +47050,7 @@
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls:
     - https://github.com/0xShug0/audio.cpp
+    - https://github.com/NVIDIA/NeMo
   description: |
     MarbleNet VAD (audio.cpp) - NeMo voice activity detection over /v1/vad, an
     alternative to Silero with different segment boundaries. The model ships