diff --git a/conversion/qwen3tts.py b/conversion/qwen3tts.py
index f52e6ac508..206978f06b 100644
--- a/conversion/qwen3tts.py
+++ b/conversion/qwen3tts.py
@@ -235,7 +235,10 @@ class Qwen3TTSSpeakerEncoderModel(MmprojModel):
         self.gguf_writer.add_audio_attention_layernorm_eps(1e-5)
 
         # handle code predictor config
+        self.gguf_writer.add_clip_has_gen_audio_encoder(True)
+        self.gguf_writer.add_clip_gen_audio_projector_type(gguf.VisionProjectorType.QWEN3TTS_GEN)
         code_predictor_config = self.global_config["talker_config"]["code_predictor_config"]
+        self.gguf_writer.add_gen_audio_projection_dim(self.n_embd_text)
         self.gguf_writer.add_gen_audio_embedding_length(code_predictor_config["hidden_size"])
         self.gguf_writer.add_gen_audio_feed_forward_length(code_predictor_config["intermediate_size"])
         self.gguf_writer.add_gen_audio_block_count(code_predictor_config["num_hidden_layers"])
diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py
index ea46ac3af2..469940b950 100644
--- a/gguf-py/gguf/constants.py
+++ b/gguf-py/gguf/constants.py
@@ -322,6 +322,7 @@ class Keys:
         PROJECTOR_TYPE        = "clip.projector_type"
         HAS_VISION_ENCODER    = "clip.has_vision_encoder"
         HAS_AUDIO_ENCODER     = "clip.has_audio_encoder"
+        HAS_GEN_AUDIO_ENCODER = "clip.has_gen_audio_encoder"
         HAS_LLAVA_PROJECTOR   = "clip.has_llava_projector"
 
     class ClipVision:
@@ -396,9 +397,11 @@ class Keys:
             HEAD_COUNT      = "clip.audio.projector.head_count"
 
     class ClipGenAudio:
+        PROJECTOR_TYPE      = "clip.gen.audio.projector_type" # for mixed modality models
         EMBEDDING_LENGTH    = "clip.gen.audio.embedding_length"
         FEED_FORWARD_LENGTH = "clip.gen.audio.feed_forward_length"
         BLOCK_COUNT         = "clip.gen.audio.block_count"
+        PROJECTION_DIM      = "clip.gen.audio.projection_dim"
 
         class Attention:
             HEAD_COUNT      = "clip.gen.audio.attention.head_count"
@@ -1607,14 +1610,14 @@ TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
     MODEL_TENSOR.A_GEN_CODE_EMBD:           "a.gen.code.embd",
     MODEL_TENSOR.A_GEN_CODE_HEAD:           "a.gen.code.head",
     MODEL_TENSOR.A_GEN_CODE_OUT_EMBD:       "a.gen.code.out_embd",
-    MODEL_TENSOR.A_GEN_CODE_ATTN_NORM:      "a.gen.code.blk.{bid}.attn_norm",
+    MODEL_TENSOR.A_GEN_CODE_ATTN_NORM:      "a.gen.code.blk.{bid}.ln1", # reuses the generic clip.cpp block loader (TN_LN_1)
     MODEL_TENSOR.A_GEN_CODE_ATTN_Q:         "a.gen.code.blk.{bid}.attn_q",
     MODEL_TENSOR.A_GEN_CODE_ATTN_Q_NORM:    "a.gen.code.blk.{bid}.attn_q_norm",
     MODEL_TENSOR.A_GEN_CODE_ATTN_K:         "a.gen.code.blk.{bid}.attn_k",
     MODEL_TENSOR.A_GEN_CODE_ATTN_K_NORM:    "a.gen.code.blk.{bid}.attn_k_norm",
     MODEL_TENSOR.A_GEN_CODE_ATTN_V:         "a.gen.code.blk.{bid}.attn_v",
     MODEL_TENSOR.A_GEN_CODE_ATTN_OUT:       "a.gen.code.blk.{bid}.attn_out",
-    MODEL_TENSOR.A_GEN_CODE_FFN_NORM:       "a.gen.code.blk.{bid}.ffn_norm",
+    MODEL_TENSOR.A_GEN_CODE_FFN_NORM:       "a.gen.code.blk.{bid}.ln2", # reuses the generic clip.cpp block loader (TN_LN_2)
     MODEL_TENSOR.A_GEN_CODE_FFN_GATE:       "a.gen.code.blk.{bid}.ffn_gate",
     MODEL_TENSOR.A_GEN_CODE_FFN_UP:         "a.gen.code.blk.{bid}.ffn_up",
     MODEL_TENSOR.A_GEN_CODE_FFN_DOWN:       "a.gen.code.blk.{bid}.ffn_down",
@@ -4965,6 +4968,7 @@ class VisionProjectorType:
     YOUTUVL = "youtuvl"
     NEMOTRON_V2_VL = "nemotron_v2_vl"
     QWEN3TTS_SPKENC = "qwen3tts_spkenc" # audio: ECAPA-TDNN speaker encoder
+    QWEN3TTS_GEN = "qwen3tts_gen" # audio generation: code_predictor
     HUNYUANVL      = "hunyuanvl"
     PARAKEET       = "parakeet"  # audio
     MINIMAXM3      = "minimax_m3"
diff --git a/gguf-py/gguf/gguf_writer.py b/gguf-py/gguf/gguf_writer.py
index 2ef09759c5..b30a0954e5 100644
--- a/gguf-py/gguf/gguf_writer.py
+++ b/gguf-py/gguf/gguf_writer.py
@@ -1199,6 +1199,9 @@ class GGUFWriter:
     def add_clip_has_audio_encoder(self, value: bool) -> None:
         self.add_bool(Keys.Clip.HAS_AUDIO_ENCODER, value)
 
+    def add_clip_has_gen_audio_encoder(self, value: bool) -> None:
+        self.add_bool(Keys.Clip.HAS_GEN_AUDIO_ENCODER, value)
+
     def add_clip_projector_type(self, value: str) -> None:
         self.add_string(Keys.Clip.PROJECTOR_TYPE, value)
 
@@ -1398,11 +1401,17 @@ class GGUFWriter:
     def add_audio_projector_head_count(self, value: int) -> None:
         self.add_uint32(Keys.ClipAudio.Projector.HEAD_COUNT, value)
 
-    def add_gen_audio_embedding_length(self, value: int) -> None:
-            self.add_uint32(Keys.ClipGenAudio.EMBEDDING_LENGTH, value)
-
     # audio generation (mmproj)
 
+    def add_clip_gen_audio_projector_type(self, value: str) -> None:
+        self.add_string(Keys.ClipGenAudio.PROJECTOR_TYPE, value)
+
+    def add_gen_audio_projection_dim(self, value: int) -> None:
+        self.add_uint32(Keys.ClipGenAudio.PROJECTION_DIM, value)
+
+    def add_gen_audio_embedding_length(self, value: int) -> None:
+        self.add_uint32(Keys.ClipGenAudio.EMBEDDING_LENGTH, value)
+
     def add_gen_audio_feed_forward_length(self, value: int) -> None:
         self.add_uint32(Keys.ClipGenAudio.FEED_FORWARD_LENGTH, value)
 
diff --git a/tools/mtmd/clip-impl.h b/tools/mtmd/clip-impl.h
index f73e80a8aa..b86adc5688 100644
--- a/tools/mtmd/clip-impl.h
+++ b/tools/mtmd/clip-impl.h
@@ -32,6 +32,7 @@
 #define KEY_PROJ_TYPE           "clip.projector_type"
 #define KEY_HAS_AUDIO_ENC       "clip.has_audio_encoder"
 #define KEY_HAS_VISION_ENC      "clip.has_vision_encoder"
+#define KEY_HAS_GEN_AUDIO_ENC   "clip.has_gen_audio_encoder"
 #define KEY_USE_GELU            "clip.use_gelu"
 #define KEY_USE_SILU            "clip.use_silu"
 
@@ -88,6 +89,8 @@
 #define KEY_A_ATTN_WINDOW_SIZE     "clip.audio.window_size"          // mimo-audio-tokenizer: sliding-window radius
 #define KEY_A_LOCAL_BLOCK_COUNT    "clip.audio.local_block_count"    // mimo-v2.5: input_local_transformer layer count
 #define KEY_A_LOCAL_GROUP_SIZE     "clip.audio.local_group_size"     // mimo-v2.5: input_local_transformer grouping size
+// audio generation (gen-audio)-specific
+#define KEY_GEN_AUDIO_PROJ_TYPE    "clip.gen.audio.projector_type" // for models with mixed modalities
 #define KEY_AUDIO_SUBSAMPLING_FACTOR "clip.audio.subsampling_factor"
 
 //
@@ -207,6 +210,13 @@
 #define TN_A_ASP_ATTN  "a.asp_attn.%s"
 #define TN_A_ASP_TDNN  "a.asp_tdnn.%s"
 
+// qwen3tts code_predictor
+#define TN_A_GEN_CODE_PROJ_IN  "a.gen.code.proj_in.%s"
+#define TN_A_GEN_CODE_EMBD     "a.gen.code.embd.%s"
+#define TN_A_GEN_CODE_HEAD     "a.gen.code.head.%s"
+#define TN_A_GEN_CODE_OUT_EMBD "a.gen.code.out_embd.%s"
+#define TN_A_GEN_CODE_NORM     "a.gen.code.output_norm.%s"
+
 // cogvlm
 #define TN_MM_POST_FC_NORM "mm.post_fc_norm.%s"
 #define TN_MM_H_TO_4H      "mm.up.%s"
@@ -415,6 +425,7 @@ enum projector_type {
     PROJECTOR_TYPE_GRANITE4_VISION,
     PROJECTOR_TYPE_MIMO_AUDIO,
     PROJECTOR_TYPE_QWEN3TTS_SPKENC,
+    PROJECTOR_TYPE_QWEN3TTS_GEN,
     PROJECTOR_TYPE_UNKNOWN,
 };
 
@@ -471,8 +482,9 @@ static std::map<projector_type, std::string> PROJECTOR_TYPE_NAMES = {
     { PROJECTOR_TYPE_MINIMAX_M3,        "minimax_m3"},
     { PROJECTOR_TYPE_GRANITE4_VISION,   "granite4_vision"},
     { PROJECTOR_TYPE_MIMO_AUDIO,        "mimo_audio"},
-    { PROJECTOR_TYPE_QWEN3TTS_SPKENC,   "qwen3tts_spkenc"},
     { PROJECTOR_TYPE_PARAKEET,          "parakeet"},
+    { PROJECTOR_TYPE_QWEN3TTS_SPKENC,   "qwen3tts_spkenc"},
+    { PROJECTOR_TYPE_QWEN3TTS_GEN,      "qwen3tts_gen"},
 };
 
 static projector_type clip_projector_type_from_string(const std::string & str) {
diff --git a/tools/mtmd/clip-model.h b/tools/mtmd/clip-model.h
index 07d36b6b9c..3cf513c943 100644
--- a/tools/mtmd/clip-model.h
+++ b/tools/mtmd/clip-model.h
@@ -592,6 +592,14 @@ struct clip_model {
     ggml_tensor * spk_asp_tdnn_w = nullptr;
     ggml_tensor * spk_asp_tdnn_b = nullptr;
 
+    // qwen3tts code_predictor
+    ggml_tensor * gen_code_proj_in_w  = nullptr; // small_to_mtp_projection
+    ggml_tensor * gen_code_proj_in_b  = nullptr;
+    ggml_tensor * gen_code_embd_w     = nullptr; // per-codebook embedding, merged 3D
+    ggml_tensor * gen_code_head_w     = nullptr; // per-codebook output head, merged 3D
+    ggml_tensor * gen_code_out_embd_w = nullptr; // codebook-0 embedding, fed back into the talker
+    ggml_tensor * gen_code_norm_w     = nullptr; // final norm
+
     // cogvlm
     ggml_tensor * mm_post_fc_norm_w = nullptr;
     ggml_tensor * mm_post_fc_norm_b = nullptr;
diff --git a/tools/mtmd/clip.cpp b/tools/mtmd/clip.cpp
index 73e9947824..c43c0d2572 100644
--- a/tools/mtmd/clip.cpp
+++ b/tools/mtmd/clip.cpp
@@ -1069,8 +1069,9 @@ struct clip_model_loader {
 
     size_t model_size = 0; // in bytes
 
-    bool has_vision = false;
-    bool has_audio  = false;
+    bool has_vision    = false;
+    bool has_audio     = false;
+    bool has_gen_audio = false;
 
     mtmd_progress_callback progress_callback = nullptr;
     void * progress_callback_user_data = nullptr;
@@ -1116,8 +1117,9 @@ struct clip_model_loader {
 
         // modalities
         {
-            get_bool(KEY_HAS_VISION_ENC, has_vision, false);
-            get_bool(KEY_HAS_AUDIO_ENC,  has_audio,  false);
+            get_bool(KEY_HAS_VISION_ENC,    has_vision,    false);
+            get_bool(KEY_HAS_AUDIO_ENC,     has_audio,     false);
+            get_bool(KEY_HAS_GEN_AUDIO_ENC, has_gen_audio, false);
 
             if (has_vision) {
                 LOG_INF("%s: has vision encoder\n", __func__);
@@ -1125,6 +1127,9 @@ struct clip_model_loader {
             if (has_audio) {
                 LOG_INF("%s: has audio encoder\n", __func__);
             }
+            if (has_gen_audio) {
+                LOG_INF("%s: has audio generation (gen) encoder\n", __func__);
+            }
         }
 
         // tensors
@@ -1151,6 +1156,8 @@ struct clip_model_loader {
             GGML_ASSERT(has_vision);
         } else if (modality == CLIP_MODALITY_AUDIO) {
             GGML_ASSERT(has_audio);
+        } else if (modality == CLIP_MODALITY_GEN_AUDIO) {
+            GGML_ASSERT(has_gen_audio);
         }
         model.modality = modality;
 
@@ -1167,6 +1174,8 @@ struct clip_model_loader {
                     get_string(KEY_VISION_PROJ_TYPE, proj_type, false);
                 } else if (modality == CLIP_MODALITY_AUDIO) {
                     get_string(KEY_AUDIO_PROJ_TYPE, proj_type, false);
+                } else if (modality == CLIP_MODALITY_GEN_AUDIO) {
+                    get_string(KEY_GEN_AUDIO_PROJ_TYPE, proj_type, false);
                 } else {
                     GGML_ABORT("unknown modality");
                 }
@@ -1186,12 +1195,13 @@ struct clip_model_loader {
             }
         }
 
-        const bool is_vision = model.modality == CLIP_MODALITY_VISION;
-        const bool is_audio  = model.modality == CLIP_MODALITY_AUDIO;
+        const bool is_vision    = model.modality == CLIP_MODALITY_VISION;
+        const bool is_audio     = model.modality == CLIP_MODALITY_AUDIO;
+        const bool is_gen_audio = model.modality == CLIP_MODALITY_GEN_AUDIO;
 
         // other hparams
         {
-            const char * prefix = is_vision ? "vision" : "audio";
+            const char * prefix = is_vision ? "vision" : (is_audio ? "audio" : "gen.audio");
             get_u32(string_format(KEY_N_EMBD,         prefix), hparams.n_embd);
             get_u32(string_format(KEY_N_HEAD,         prefix), hparams.n_head);
             get_u32(string_format(KEY_N_FF,           prefix), hparams.n_ff);
@@ -1229,6 +1239,11 @@ struct clip_model_loader {
                 hparams.image_size = 0;
                 hparams.patch_size = 1;
 
+            } else if (is_gen_audio) {
+                // these are unused, but still need to be set to avoid issues
+                hparams.image_size = 0;
+                hparams.patch_size = 1;
+
             } else {
                 GGML_ASSERT(false && "unknown modality");
             }
@@ -1658,6 +1673,10 @@ struct clip_model_loader {
                         hparams.audio_window_len  = 1024;
                         hparams.audio_hop_len     = 256;
                     } break;
+                case PROJECTOR_TYPE_QWEN3TTS_GEN:
+                    {
+                        // discrete-token autoregressive predictor, no mel-frontend needed
+                    } break;
                 case PROJECTOR_TYPE_PADDLEOCR:
                     {
                         hparams.n_merge = 2;
@@ -1882,7 +1901,9 @@ struct clip_model_loader {
         }
 
         // TODO @ngxson : support both audio and video in the future
-        const char * prefix = model.modality == CLIP_MODALITY_AUDIO ? "a" : "v";
+        const char * prefix = model.modality == CLIP_MODALITY_AUDIO ? "a"
+                             : model.modality == CLIP_MODALITY_GEN_AUDIO ? "a.gen.code"
+                             : "v";
 
         // get offsets
         for (int64_t i = 0; i < gguf_get_n_tensors(ctx_gguf.get()); ++i) {
@@ -2647,6 +2668,16 @@ struct clip_model_loader {
                     model.mm_fc_w = get_tensor(string_format(TN_MM_AUDIO_FC, "weight"));
                     model.mm_fc_b = get_tensor(string_format(TN_MM_AUDIO_FC, "bias"));
                 } break;
+            case PROJECTOR_TYPE_QWEN3TTS_GEN:
+                {
+                    // code_predictor
+                    model.gen_code_proj_in_w = get_tensor(string_format(TN_A_GEN_CODE_PROJ_IN, "weight"));
+                    model.gen_code_proj_in_b = get_tensor(string_format(TN_A_GEN_CODE_PROJ_IN, "bias"));
+                    model.gen_code_embd_w     = get_tensor(string_format(TN_A_GEN_CODE_EMBD,     "weight"));
+                    model.gen_code_head_w     = get_tensor(string_format(TN_A_GEN_CODE_HEAD,     "weight"));
+                    model.gen_code_out_embd_w = get_tensor(string_format(TN_A_GEN_CODE_OUT_EMBD, "weight"));
+                    model.gen_code_norm_w     = get_tensor(string_format(TN_A_GEN_CODE_NORM,     "weight"));
+                } break;
             case PROJECTOR_TYPE_VOXTRAL:
                 {
                     model.conv1d_1_w = get_tensor(string_format(TN_CONV1D, 1, "weight"));
@@ -3475,6 +3506,7 @@ struct clip_model_loader {
 struct clip_init_result clip_init(const char * fname, struct clip_context_params ctx_params) {
     clip_ctx * ctx_vision = nullptr;
     clip_ctx * ctx_audio = nullptr;
+    clip_ctx * ctx_gen_audio = nullptr;
 
     try {
         clip_model_loader loader(fname,
@@ -3507,16 +3539,23 @@ struct clip_init_result clip_init(const char * fname, struct clip_context_params
             }
         }
 
+        if (loader.has_gen_audio) {
+            ctx_gen_audio = new clip_ctx(ctx_params);
+            loader.load_hparams(ctx_gen_audio->model, CLIP_MODALITY_GEN_AUDIO);
+            loader.load_tensors(*ctx_gen_audio);
+        }
+
     } catch (const std::exception & e) {
         LOG_ERR("%s: failed to load model '%s': %s\n", __func__, fname, e.what());
 
         delete ctx_vision;
         delete ctx_audio;
+        delete ctx_gen_audio;
 
-        return {nullptr, nullptr};
+        return {nullptr, nullptr, nullptr};
     }
 
-    return {ctx_vision, ctx_audio};
+    return {ctx_vision, ctx_audio, ctx_gen_audio};
 }
 
 struct clip_cap clip_get_cap(const char * fname) {
diff --git a/tools/mtmd/clip.h b/tools/mtmd/clip.h
index 967093a812..18836ecd0c 100644
--- a/tools/mtmd/clip.h
+++ b/tools/mtmd/clip.h
@@ -37,6 +37,7 @@ struct clip_image_f32_batch;
 enum clip_modality {
     CLIP_MODALITY_VISION,
     CLIP_MODALITY_AUDIO,
+    CLIP_MODALITY_GEN_AUDIO,
 };
 
 enum clip_flash_attn_type {
@@ -61,6 +62,7 @@ struct clip_context_params {
 struct clip_init_result {
     struct clip_ctx * ctx_v; // vision context
     struct clip_ctx * ctx_a; // audio context
+    struct clip_ctx * ctx_gen_a; // audio generation context
 };
 
 struct clip_init_result clip_init(const char * fname, struct clip_context_params ctx_params);
diff --git a/tools/mtmd/mtmd.cpp b/tools/mtmd/mtmd.cpp
index 4841cde564..5e83bf039a 100644
--- a/tools/mtmd/mtmd.cpp
+++ b/tools/mtmd/mtmd.cpp
@@ -262,6 +262,9 @@ struct mtmd_context {
     struct clip_ctx * ctx_a; // audio
     std::vector<float> out_embd; // image embedding vector
 
+    // generation context
+    struct clip_ctx * ctx_gen_a; // audio
+
     bool print_timings;
     int n_threads;
     std::string media_marker;
@@ -354,6 +357,7 @@ struct mtmd_context {
         auto res = clip_init(mmproj_fname, ctx_clip_params);
         ctx_v = res.ctx_v;
         ctx_a = res.ctx_a;
+        ctx_gen_a = res.ctx_gen_a;
         if (!ctx_v && !ctx_a) {
             throw std::runtime_error(string_format("Failed to load CLIP model from %s\n", mmproj_fname));
         }
@@ -784,6 +788,7 @@ struct mtmd_context {
     ~mtmd_context() {
         clip_free(ctx_a);
         clip_free(ctx_v);
+        clip_free(ctx_gen_a);
     }
 
 private: