feat(gallery): add Higgs Audio v3 TTS (#11456)

Expose the existing audio.cpp Higgs support as an installable Q8 gallery model and document voice cloning and licensing constraints.

Assisted-by: Codex:gpt-5

Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>

Author: localai-org-maint-bot

core/gallery/variants_lint_test.go

@@ -11,6 +11,7 @@ import (
 	. "github.com/onsi/gomega"
 	"gopkg.in/yaml.v3"
 
+	"github.com/mudler/LocalAI/core/config"
 	"github.com/mudler/LocalAI/core/gallery"
 )
 
@@ -517,6 +518,28 @@ var _ = Describe("gallery/index.yaml variant invariants", Ordered, func() {
 	})
 })
 
+var _ = Describe("gallery/index.yaml Higgs Audio entry", func() {
+	It("installs the validated Q8 model through audio-cpp for TTS", func() {
+		entries, err := loadGalleryIndex()
+		Expect(err).ToNot(HaveOccurred())
+
+		models := make([]*gallery.GalleryModel, 0, len(entries))
+		for i := range entries {
+			models = append(models, &entries[i])
+		}
+		entry := gallery.FindGalleryElement(models, "audio-cpp-higgs-audio-v3")
+		Expect(entry).ToNot(BeNil())
+		Expect(entry.Overrides).To(HaveKeyWithValue("backend", "audio-cpp"))
+		Expect(entry.GetKnownUsecases()).ToNot(BeNil())
+		Expect(*entry.GetKnownUsecases() & config.FLAG_TTS).To(Equal(config.FLAG_TTS))
+		Expect(entry.AdditionalFiles).To(ConsistOf(gallery.File{
+			Filename: "audio-cpp/higgs-audio-v3-tts-4b-q8_0.gguf",
+			SHA256:   "b857344af06b1b2497f4f8c1d0f0c134d0eeaf9c089c0d28ae6e58084d90f901",
+			URI:      "huggingface://audio-cpp/audio.cpp-gguf/Higgs-Audio-v3-TTS-4B-GGUF/higgs-audio-v3-tts-4b-q8_0.gguf",
+		}))
+	})
+})
+
 // The lint rules above check the catalog as text. This drives the real
 // resolution path for the entry a user actually clicked and failed to install,
 // so the fix is proven at the layer that broke and not only at the layer that

docs/content/features/text-to-audio.md

@@ -807,6 +807,26 @@ one installed backend covers TTS (`supertonic`, `vibevoice`, `voxcpm2`, `fish_au
 `irodori_tts`, `moss_tts_local`, `moss_tts_nano`) and voice design (`qwen3_tts`, `irodori_tts`), alongside ASR, VAD,
 diarization and separation.
 
+Higgs Audio v3 is available directly from the model gallery as
+`audio-cpp-higgs-audio-v3`. It uses the Q8_0 GGUF validated by audio.cpp and supports
+expressive multilingual TTS and zero-shot voice cloning. For cloning, pass the path to a
+server-local WAV file in the OpenAI `voice` field. Use only reference audio for which you
+have the necessary rights and consent, and review the model's research and non-commercial
+license before deployment.
+
+```bash
+local-ai models install audio-cpp-higgs-audio-v3
+
+curl http://localhost:8080/v1/audio/speech \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "audio-cpp-higgs-audio-v3",
+    "input": "Welcome to LocalAI.",
+    "voice": "/models/voices/reference.wav"
+  }' \
+  --output higgs.wav
+```
+
 ```yaml
 name: supertonic
 backend: audio-cpp

gallery/index.yaml

@@ -50100,6 +50100,48 @@
     - filename: audio-cpp/supertonic-3-orig.gguf
       sha256: af814486a0bc9513fb36afabd9b1155ad14fb2c36a107ac6ffe62ea9adafb662
       uri: huggingface://audio-cpp/audio.cpp-gguf/Supertonic-3-GGUF/supertonic-3-orig.gguf
+- name: audio-cpp-higgs-audio-v3
+  url: github:mudler/LocalAI/gallery/virtual.yaml@master
+  urls:
+    - https://huggingface.co/bosonai/higgs-tts-3-4b
+    - https://huggingface.co/audio-cpp/audio.cpp-gguf
+    - https://github.com/0xShug0/audio.cpp
+  description: |
+    Higgs Audio v3 TTS 4B (audio.cpp, Q8_0) - expressive conversational
+    speech in more than 100 languages, with zero-shot voice cloning and inline
+    control over emotion, style, prosody, pauses and sound effects.
+
+    Supply a server-local WAV path in the OpenAI `voice` field to clone a
+    speaker, and use only audio for which you have the necessary rights and
+    consent. The Q8_0 GGUF is the recommended quality and speed balance and is
+    recorded as passing upstream's audio.cpp validation.
+
+    The Boson Higgs TTS 3 Research and Non-Commercial License permits research
+    and non-commercial use. Its creator-use grant and commercial-use terms
+    carry additional conditions; review the model license before deployment.
+  license: other
+  tags:
+    - audio-cpp
+    - higgs-audio
+    - multilingual
+    - tts
+    - text-to-speech
+    - voice-cloning
+    - gguf
+    - ggml
+    - quantized
+  last_checked: "2026-08-11"
+  overrides:
+    backend: audio-cpp
+    known_usecases:
+      - tts
+    name: audio-cpp-higgs-audio-v3
+    parameters:
+      model: audio-cpp/higgs-audio-v3-tts-4b-q8_0.gguf
+  files:
+    - filename: audio-cpp/higgs-audio-v3-tts-4b-q8_0.gguf
+      sha256: b857344af06b1b2497f4f8c1d0f0c134d0eeaf9c089c0d28ae6e58084d90f901
+      uri: huggingface://audio-cpp/audio.cpp-gguf/Higgs-Audio-v3-TTS-4B-GGUF/higgs-audio-v3-tts-4b-q8_0.gguf
 - name: audio-cpp-chatterbox
   url: github:mudler/LocalAI/gallery/virtual.yaml@master
   urls: