Move Breeze voice design to design route

Author: 0xShug0

model_specs/breeze_tts.json

@@ -7,7 +7,8 @@
   "status": "supported",
   "tasks": [
     "tts",
-    "clone"
+    "clone",
+    "design"
   ],
   "modes": [
     "offline"
@@ -23,6 +24,9 @@
   },
   "dependencies": [],
   "capabilities": {
+    "design": [
+      "voice_design"
+    ],
     "tts": [
       "style_control"
     ],
@@ -174,7 +178,7 @@
       "strip_prefix": "Breeze-TTS-2-GGUF",
       "download": {
         "kind": "huggingface_snapshot",
-        "repo": "audio-cpp/Breeze-TTS-2-GGUF",
+        "repo": "audio-cpp/audio.cpp-gguf",
         "revision": "main",
         "gated": false
       }
@@ -192,7 +196,7 @@
       "strip_prefix": "Breeze-TTS-2-GGUF",
       "download": {
         "kind": "huggingface_snapshot",
-        "repo": "audio-cpp/Breeze-TTS-2-GGUF",
+        "repo": "audio-cpp/audio.cpp-gguf",
         "revision": "main",
         "gated": false
       }
@@ -203,6 +207,7 @@
     "tags": [
       "TTS",
       "Clone",
+      "Design",
       "GGUF"
     ],
     "docs": [

model_specs/cosyvoice3.json

@@ -192,7 +192,7 @@
       "strip_prefix": "CosyVoice3-GGUF",
       "download": {
         "kind": "huggingface_snapshot",
-        "repo": "audio-cpp/CosyVoice3-GGUF",
+        "repo": "audio-cpp/audio.cpp-gguf",
         "revision": "main",
         "gated": false
       }
@@ -210,7 +210,7 @@
       "strip_prefix": "CosyVoice3-GGUF",
       "download": {
         "kind": "huggingface_snapshot",
-        "repo": "audio-cpp/CosyVoice3-GGUF",
+        "repo": "audio-cpp/audio.cpp-gguf",
         "revision": "main",
         "gated": false
       }

src/models/breeze_tts/session.cpp

@@ -101,8 +101,10 @@ BreezeTTSSession::BreezeTTSSession(
       contract_(require_contract(std::move(contract))),
       reference_cache_(reference_cache_slots_from_options(options)) {
     runtime::validate_spec_backed_session_options(options, *contract_, kFamily, kModelName);
-    if (task_.task != runtime::VoiceTaskKind::Tts && task_.task != runtime::VoiceTaskKind::VoiceCloning) {
-        throw std::runtime_error("BreezeTTS supports tts and clone tasks");
+    if (task_.task != runtime::VoiceTaskKind::Tts &&
+        task_.task != runtime::VoiceTaskKind::VoiceCloning &&
+        task_.task != runtime::VoiceTaskKind::VoiceDesign) {
+        throw std::runtime_error("BreezeTTS supports tts, clone, and voice design tasks");
     }
     if (task_.mode != runtime::RunMode::Offline) {
         throw std::runtime_error("BreezeTTS supports offline sessions");

webui/configs/model_params.json

@@ -101,6 +101,16 @@
     {"name": "top_p", "type": "slider", "label": "top_p", "default": 1.0, "minimum": 0.0, "maximum": 1.0, "step": 0.01}
   ],
 
+  "breeze-tts": [
+    {"name": "text_chunk_size", "type": "number", "label": "text_chunk_size", "default": 600, "minimum": 1, "step": 1, "precision": 0},
+    {"name": "text_chunk_mode", "type": "choice", "label": "text_chunk_mode", "default": "default", "choices": ["default", "tag_aware", "japanese", "endline"]},
+    {"name": "guidance_scale", "type": "slider", "label": "guidance_scale", "default": 1.0, "minimum": 0.0, "maximum": 10.0, "step": 0.1},
+    {"name": "temperature", "type": "slider", "label": "temperature", "default": 0.9, "minimum": 0.0, "maximum": 2.0, "step": 0.05},
+    {"name": "depth_temperature", "type": "slider", "label": "depth_temperature", "default": 0.9, "minimum": 0.0, "maximum": 2.0, "step": 0.05},
+    {"name": "top_k", "type": "number", "label": "top_k", "default": 50, "minimum": 0, "step": 1, "precision": 0},
+    {"name": "top_p", "type": "slider", "label": "top_p", "default": 1.0, "minimum": 0.0, "maximum": 1.0, "step": 0.01}
+  ],
+
   "cosyvoice3": [
     {"name": "template_name", "type": "choice", "label": "template_name", "default": "zero_shot", "choices": ["zero_shot", "cross_lingual", "instruct"]},
     {"name": "instruction", "type": "text", "label": "instruction", "label_en": "Instruction", "default": "", "placeholder": "Used by template_name=instruct."},

webui/configs/models_catalog.json

@@ -14,7 +14,7 @@
     { "id": "qwen3-tts",              "display_name": "Qwen3-TTS 0.6B (tts)",                  "family": "qwen3_tts",            "path": "models/Qwen3-TTS-12Hz-0.6B-Base",        "task": "tts",   "mode": "offline", "download_id": "qwen3_tts_0_6b_base",     "min_vram_gb": 5 },
     { "id": "qwen3-tts-1.7b",         "display_name": "Qwen3-TTS 1.7B Base (tts)",             "family": "qwen3_tts",            "path": "models/Qwen3-TTS-12Hz-1.7B-Base",        "task": "tts",   "mode": "offline", "download_id": "qwen3_tts_1_7b_base",     "min_vram_gb": 8 },
     { "id": "qwen3-tts-1.7b-custom",  "display_name": "Qwen3-TTS 1.7B CustomVoice (tts)",      "family": "qwen3_tts",            "path": "models/Qwen3-TTS-12Hz-1.7B-CustomVoice", "task": "tts",   "mode": "offline", "download_id": "qwen3_tts_1_7b_custom_voice", "min_vram_gb": 8 },
-    { "id": "breeze-tts",             "display_name": "BreezeTTS 2 VoiceDesign",               "family": "breeze_tts",           "path": "models/Breeze-TTS-2-GGUF/breeze-tts-2-q8_0.gguf", "task": "tts", "mode": "offline", "download_id": "breeze_tts_2_q8_0", "min_vram_gb": 8,
+    { "id": "breeze-tts",             "display_name": "BreezeTTS 2 VoiceDesign",               "family": "breeze_tts",           "path": "models/Breeze-TTS-2-GGUF/breeze-tts-2-q8_0.gguf", "task": "vdes", "mode": "offline", "download_id": "breeze_tts_2_q8_0", "min_vram_gb": 8,
       "input_hint_en": "**BreezeTTS 2 VoiceDesign**: enter text and describe the target voice in Model parameters. No reference voice is required." },
     { "id": "breeze-tts-clone",       "display_name": "BreezeTTS 2 Clone",                     "family": "breeze_tts",           "path": "models/Breeze-TTS-2-GGUF/breeze-tts-2-q8_0.gguf", "task": "clon", "mode": "offline", "download_id": "breeze_tts_2_q8_0", "min_vram_gb": 8,
       "input_hint_en": "**BreezeTTS 2 Clone**: upload a reference voice and provide the matching reference transcript." },