gallery(audio-cpp): add voice-design and singing-voice-conversion entries

Two of the three audio.cpp task kinds that had no gallery model now have one.
Both were driven end to end against the real weights through the backend
before being written, not inferred from the capability tables.

audio-cpp-irodori-voicedesign covers vdes. TTS carrying `instructions` routes
to the vdes task, so the voice is described in words rather than supplied as a
clip. Verified: "a calm elderly woman speaking slowly with a warm, gentle
tone" over an 8.76 s 48 kHz mono render at -16.8 dB mean, and a closed-loop
citrinet pass recovers the sentence with the accent drift expected from a
Japanese-first model read by an English recogniser.

audio-cpp-seedvc-singing covers svc, and pins task:svc because nothing else
can reach it. seed_vc advertises svc and ordinary voice conversion, no request
signal means "this input is singing", and auto-routing resolves the tie to
voice conversion every time. Verified with the pin: 5.04 s 44.1 kHz output
whose closed-loop citrinet transcription is exact.

s2s deliberately has no entry, and the reason is not effort. miocodec is the
only upstream family whose speech-to-speech route needs no text, and it
returned audio with correct duration and level but no recoverable speech in
four independent attempts: the stale build, v2 q8_0, v2 orig (the variant
upstream records as a clean Pass), both tasks, and matched 44.1 kHz inputs on
both sides. vevo2's route refuses with "Vevo2 text/prosody route requires
text_input or target_text", and session.cpp:897 fills target_text only from
request.text_input, which AudioTransform has no field to carry. The same
vevo2 weights convert voice correctly through the default route with an exact
ASR round trip, so the model and the plumbing are both healthy; it is the s2s
route specifically that this RPC cannot express.

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

gallery/index.yaml

@@ -47082,3 +47082,90 @@
       - family:marblenet_vad
     parameters:
       model: bundled:marblenet_vad
+- name: audio-cpp-irodori-voicedesign
+  url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  urls:
+    - https://huggingface.co/audio-cpp/audio.cpp-gguf
+    - https://huggingface.co/Aratako/Irodori-TTS-600M-v3-VoiceDesign
+    - https://github.com/0xShug0/audio.cpp
+  description: |
+    Irodori TTS 600M v3 VoiceDesign (audio.cpp, Q8_0) - describe the voice you
+    want in words instead of supplying a reference clip, served by the
+    audio-cpp backend.
+
+    Drive it through /v1/audio/speech with the `instructions` field: the
+    backend routes a request carrying instructions to audio.cpp's vdes task, so
+    "a calm elderly woman speaking slowly with a warm, gentle tone" shapes the
+    delivery of whatever you put in `input`. Without instructions this build
+    still answers as ordinary TTS, and with a reference WAV in `voice` it
+    clones instead; the request decides which of the three it gets.
+
+    The model is Japanese-first and handles English, so an English ASR round
+    trip recovers the words with accent drift rather than cleanly.
+  license: mit
+  tags:
+    - audio-cpp
+    - irodori
+    - tts
+    - text-to-speech
+    - voice-design
+    - gguf
+    - ggml
+    - quantized
+  last_checked: "2026-07-27"
+  overrides:
+    backend: audio-cpp
+    known_usecases:
+      - tts
+    name: audio-cpp-irodori-voicedesign
+    parameters:
+      model: audio-cpp/irodori-tts-600m-v3-voicedesign-q8_0.gguf
+  files:
+    - filename: audio-cpp/irodori-tts-600m-v3-voicedesign-q8_0.gguf
+      sha256: eda37824d020f90a5f7bf831cee8145714b35b93876651765fc516637f425b33
+      uri: huggingface://audio-cpp/audio.cpp-gguf/Irodori-TTS-600M-v3-VoiceDesign-GGUF/irodori-tts-600m-v3-voicedesign-q8_0.gguf
+- name: audio-cpp-seedvc-singing
+  url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  urls:
+    - https://huggingface.co/audio-cpp/audio.cpp-gguf
+    - https://huggingface.co/mlx-community/SeedVC-MLX
+    - https://github.com/0xShug0/audio.cpp
+  description: |
+    Seed-VC (audio.cpp, Q8_0) - singing voice conversion, served by the
+    audio-cpp backend through /audio/transform. Post the performance to convert
+    as `audio` and the target singer's clip as `reference`.
+
+    This entry pins task:svc, and the pin is what makes it a singing model
+    rather than a speech one. Seed-VC advertises both svc and ordinary voice
+    conversion, and nothing in a request says "this input is singing", so
+    auto-routing always picks voice conversion; the pin is the only way to
+    reach the singing path. Drop the option from the model config to get plain
+    voice conversion from the same weights.
+
+    Q8_0 because the 16-bit and Q8_0 builds carry the same tested status
+    upstream (drift) and this one is half the size. Note the GPL-3.0 licence,
+    which is stricter than most of the gallery.
+  license: gpl-3.0
+  tags:
+    - audio-cpp
+    - seed-vc
+    - singing-voice-conversion
+    - voice-conversion
+    - audio-transform
+    - gguf
+    - ggml
+    - quantized
+  last_checked: "2026-07-27"
+  overrides:
+    backend: audio-cpp
+    known_usecases:
+      - audio_transform
+    name: audio-cpp-seedvc-singing
+    options:
+      - task:svc
+    parameters:
+      model: audio-cpp/seed-vc-mlx-q8_0.gguf
+  files:
+    - filename: audio-cpp/seed-vc-mlx-q8_0.gguf
+      sha256: f3e2469eb29762af96f9663ce62eab6e8c40f3798c6dc0835e7613f22b4b75f7
+      uri: huggingface://audio-cpp/audio.cpp-gguf/SeedVC-MLX-GGUF/seed-vc-mlx-q8_0.gguf