@qvac/sdk 0.15.0 → 0.17.0

package/dist/schemas/text-to-speech.d.ts

@@ -1,6 +1,7 @@
 import { z } from 'zod';
 export declare const TTS_CHATTERBOX_LANGUAGES: readonly ["en", "es", "fr", "de", "it", "ja", "pt", "nl", "pl", "tr", "sv", "da", "fi", "no", "el", "ms", "sw", "ar", "ko", "he", "ru", "zh", "hi"];
 export declare const TTS_SUPERTONIC_LANGUAGES: readonly ["en", "ko", "ja", "ar", "bg", "cs", "da", "de", "el", "es", "et", "fi", "fr", "hi", "hr", "hu", "id", "it", "lt", "lv", "nl", "pl", "pt", "ro", "ru", "sk", "sl", "sv", "tr", "uk", "vi"];
+export declare const TTS_PARLER_EMOTIONS: readonly ["command", "anger", "narration", "conversation", "disgust", "fear", "happy", "neutral", "proper noun", "news", "sad", "surprise"];
 export declare const TTS_LANGUAGES: readonly ["en", "es", "fr", "de", "it", "ja", "pt", "nl", "pl", "tr", "sv", "da", "fi", "no", "el", "ms", "sw", "ar", "ko", "he", "ru", "zh", "hi", "bg", "cs", "et", "hr", "hu", "id", "lt", "lv", "ro", "sk", "sl", "uk", "vi"];
 export declare const ttsChatterboxRuntimeConfigSchema: z.ZodObject<{
     ttsEngine: z.ZodLiteral<"chatterbox">;
@@ -34,6 +35,7 @@ export declare const ttsChatterboxRuntimeConfigSchema: z.ZodObject<{
     streamChunkTokens: z.ZodOptional<z.ZodNumber>;
     streamFirstChunkTokens: z.ZodOptional<z.ZodNumber>;
     cfmSteps: z.ZodOptional<z.ZodNumber>;
+    cfgRate: z.ZodOptional<z.ZodNumber>;
     threads: z.ZodOptional<z.ZodNumber>;
     nGpuLayers: z.ZodOptional<z.ZodNumber>;
     seed: z.ZodOptional<z.ZodNumber>;
@@ -78,6 +80,46 @@ export declare const ttsSupertonicRuntimeConfigSchema: z.ZodObject<{
     ttsNumInferenceSteps: z.ZodOptional<z.ZodNumber>;
     useGPU: z.ZodOptional<z.ZodBoolean>;
     outputSampleRate: z.ZodOptional<z.ZodNumber>;
+    vulkanCacheDir: z.ZodOptional<z.ZodString>;
+}, z.core.$strip>;
+export declare const ttsParlerRuntimeConfigSchema: z.ZodObject<{
+    useGPU: z.ZodOptional<z.ZodBoolean>;
+    outputSampleRate: z.ZodOptional<z.ZodNumber>;
+    streamChunkTokens: z.ZodOptional<z.ZodNumber>;
+    streamFirstChunkTokens: z.ZodOptional<z.ZodNumber>;
+    threads: z.ZodOptional<z.ZodNumber>;
+    nGpuLayers: z.ZodOptional<z.ZodNumber>;
+    seed: z.ZodOptional<z.ZodNumber>;
+    temperature: z.ZodOptional<z.ZodNumber>;
+    topK: z.ZodOptional<z.ZodNumber>;
+    topP: z.ZodOptional<z.ZodNumber>;
+    maxFrames: z.ZodOptional<z.ZodUnion<readonly [z.ZodLiteral<0>, z.ZodNumber]>>;
+    minNewTokens: z.ZodOptional<z.ZodNumber>;
+    normalizeNumbers: z.ZodOptional<z.ZodBoolean>;
+    description: z.ZodOptional<z.ZodString>;
+    voiceDescription: z.ZodOptional<z.ZodString>;
+    voice: z.ZodOptional<z.ZodString>;
+    emotion: z.ZodOptional<z.ZodEnum<{
+        command: "command";
+        anger: "anger";
+        narration: "narration";
+        conversation: "conversation";
+        disgust: "disgust";
+        fear: "fear";
+        happy: "happy";
+        neutral: "neutral";
+        "proper noun": "proper noun";
+        news: "news";
+        sad: "sad";
+        surprise: "surprise";
+    }>>;
+    pitch: z.ZodOptional<z.ZodString>;
+    pace: z.ZodOptional<z.ZodString>;
+    expressivity: z.ZodOptional<z.ZodString>;
+    noise: z.ZodOptional<z.ZodString>;
+    reverb: z.ZodOptional<z.ZodString>;
+    quality: z.ZodOptional<z.ZodString>;
+    ttsEngine: z.ZodLiteral<"parler">;
 }, z.core.$strip>;
 export declare const ttsRuntimeConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
     ttsEngine: z.ZodLiteral<"chatterbox">;
@@ -111,6 +153,7 @@ export declare const ttsRuntimeConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObjec
     streamChunkTokens: z.ZodOptional<z.ZodNumber>;
     streamFirstChunkTokens: z.ZodOptional<z.ZodNumber>;
     cfmSteps: z.ZodOptional<z.ZodNumber>;
+    cfgRate: z.ZodOptional<z.ZodNumber>;
     threads: z.ZodOptional<z.ZodNumber>;
     nGpuLayers: z.ZodOptional<z.ZodNumber>;
     seed: z.ZodOptional<z.ZodNumber>;
@@ -154,6 +197,45 @@ export declare const ttsRuntimeConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObjec
     ttsNumInferenceSteps: z.ZodOptional<z.ZodNumber>;
     useGPU: z.ZodOptional<z.ZodBoolean>;
     outputSampleRate: z.ZodOptional<z.ZodNumber>;
+    vulkanCacheDir: z.ZodOptional<z.ZodString>;
+}, z.core.$strip>, z.ZodObject<{
+    useGPU: z.ZodOptional<z.ZodBoolean>;
+    outputSampleRate: z.ZodOptional<z.ZodNumber>;
+    streamChunkTokens: z.ZodOptional<z.ZodNumber>;
+    streamFirstChunkTokens: z.ZodOptional<z.ZodNumber>;
+    threads: z.ZodOptional<z.ZodNumber>;
+    nGpuLayers: z.ZodOptional<z.ZodNumber>;
+    seed: z.ZodOptional<z.ZodNumber>;
+    temperature: z.ZodOptional<z.ZodNumber>;
+    topK: z.ZodOptional<z.ZodNumber>;
+    topP: z.ZodOptional<z.ZodNumber>;
+    maxFrames: z.ZodOptional<z.ZodUnion<readonly [z.ZodLiteral<0>, z.ZodNumber]>>;
+    minNewTokens: z.ZodOptional<z.ZodNumber>;
+    normalizeNumbers: z.ZodOptional<z.ZodBoolean>;
+    description: z.ZodOptional<z.ZodString>;
+    voiceDescription: z.ZodOptional<z.ZodString>;
+    voice: z.ZodOptional<z.ZodString>;
+    emotion: z.ZodOptional<z.ZodEnum<{
+        command: "command";
+        anger: "anger";
+        narration: "narration";
+        conversation: "conversation";
+        disgust: "disgust";
+        fear: "fear";
+        happy: "happy";
+        neutral: "neutral";
+        "proper noun": "proper noun";
+        news: "news";
+        sad: "sad";
+        surprise: "surprise";
+    }>>;
+    pitch: z.ZodOptional<z.ZodString>;
+    pace: z.ZodOptional<z.ZodString>;
+    expressivity: z.ZodOptional<z.ZodString>;
+    noise: z.ZodOptional<z.ZodString>;
+    reverb: z.ZodOptional<z.ZodString>;
+    quality: z.ZodOptional<z.ZodString>;
+    ttsEngine: z.ZodLiteral<"parler">;
 }, z.core.$strip>], "ttsEngine">;
 export declare const ttsChatterboxLoadConfigSchema: z.ZodObject<{
     ttsEngine: z.ZodLiteral<"chatterbox">;
@@ -187,6 +269,7 @@ export declare const ttsChatterboxLoadConfigSchema: z.ZodObject<{
     streamChunkTokens: z.ZodOptional<z.ZodNumber>;
     streamFirstChunkTokens: z.ZodOptional<z.ZodNumber>;
     cfmSteps: z.ZodOptional<z.ZodNumber>;
+    cfgRate: z.ZodOptional<z.ZodNumber>;
     threads: z.ZodOptional<z.ZodNumber>;
     nGpuLayers: z.ZodOptional<z.ZodNumber>;
     seed: z.ZodOptional<z.ZodNumber>;
@@ -204,6 +287,7 @@ export declare const ttsChatterboxLoadConfigSchema: z.ZodObject<{
         addon: z.ZodOptional<z.ZodUnion<readonly [z.ZodEnum<{
             embeddings: "embeddings";
             diffusion: "diffusion";
+            audiogen: "audiogen";
             tts: "tts";
             ocr: "ocr";
             vla: "vla";
@@ -217,6 +301,7 @@ export declare const ttsChatterboxLoadConfigSchema: z.ZodObject<{
             "parakeet-transcription": "parakeet-transcription";
             "ggml-ocr": "ggml-ocr";
             "sdcpp-generation": "sdcpp-generation";
+            "audiogen-ggml": "audiogen-ggml";
             "ggml-vla": "ggml-vla";
             "ggml-classification": "ggml-classification";
             llm: "llm";
@@ -241,6 +326,7 @@ export declare const ttsChatterboxLoadConfigSchema: z.ZodObject<{
         addon: z.ZodOptional<z.ZodUnion<readonly [z.ZodEnum<{
             embeddings: "embeddings";
             diffusion: "diffusion";
+            audiogen: "audiogen";
             tts: "tts";
             ocr: "ocr";
             vla: "vla";
@@ -254,6 +340,7 @@ export declare const ttsChatterboxLoadConfigSchema: z.ZodObject<{
             "parakeet-transcription": "parakeet-transcription";
             "ggml-ocr": "ggml-ocr";
             "sdcpp-generation": "sdcpp-generation";
+            "audiogen-ggml": "audiogen-ggml";
             "ggml-vla": "ggml-vla";
             "ggml-classification": "ggml-classification";
             llm: "llm";
@@ -278,6 +365,7 @@ export declare const ttsChatterboxLoadConfigSchema: z.ZodObject<{
         addon: z.ZodOptional<z.ZodUnion<readonly [z.ZodEnum<{
             embeddings: "embeddings";
             diffusion: "diffusion";
+            audiogen: "audiogen";
             tts: "tts";
             ocr: "ocr";
             vla: "vla";
@@ -291,6 +379,7 @@ export declare const ttsChatterboxLoadConfigSchema: z.ZodObject<{
             "parakeet-transcription": "parakeet-transcription";
             "ggml-ocr": "ggml-ocr";
             "sdcpp-generation": "sdcpp-generation";
+            "audiogen-ggml": "audiogen-ggml";
             "ggml-vla": "ggml-vla";
             "ggml-classification": "ggml-classification";
             llm: "llm";
@@ -315,6 +404,7 @@ export declare const ttsChatterboxLoadConfigSchema: z.ZodObject<{
         addon: z.ZodOptional<z.ZodUnion<readonly [z.ZodEnum<{
             embeddings: "embeddings";
             diffusion: "diffusion";
+            audiogen: "audiogen";
             tts: "tts";
             ocr: "ocr";
             vla: "vla";
@@ -328,6 +418,7 @@ export declare const ttsChatterboxLoadConfigSchema: z.ZodObject<{
             "parakeet-transcription": "parakeet-transcription";
             "ggml-ocr": "ggml-ocr";
             "sdcpp-generation": "sdcpp-generation";
+            "audiogen-ggml": "audiogen-ggml";
             "ggml-vla": "ggml-vla";
             "ggml-classification": "ggml-classification";
             llm: "llm";
@@ -352,6 +443,7 @@ export declare const ttsChatterboxLoadConfigSchema: z.ZodObject<{
         addon: z.ZodOptional<z.ZodUnion<readonly [z.ZodEnum<{
             embeddings: "embeddings";
             diffusion: "diffusion";
+            audiogen: "audiogen";
             tts: "tts";
             ocr: "ocr";
             vla: "vla";
@@ -365,6 +457,7 @@ export declare const ttsChatterboxLoadConfigSchema: z.ZodObject<{
             "parakeet-transcription": "parakeet-transcription";
             "ggml-ocr": "ggml-ocr";
             "sdcpp-generation": "sdcpp-generation";
+            "audiogen-ggml": "audiogen-ggml";
             "ggml-vla": "ggml-vla";
             "ggml-classification": "ggml-classification";
             llm: "llm";
@@ -389,6 +482,7 @@ export declare const ttsChatterboxLoadConfigSchema: z.ZodObject<{
         addon: z.ZodOptional<z.ZodUnion<readonly [z.ZodEnum<{
             embeddings: "embeddings";
             diffusion: "diffusion";
+            audiogen: "audiogen";
             tts: "tts";
             ocr: "ocr";
             vla: "vla";
@@ -402,6 +496,7 @@ export declare const ttsChatterboxLoadConfigSchema: z.ZodObject<{
             "parakeet-transcription": "parakeet-transcription";
             "ggml-ocr": "ggml-ocr";
             "sdcpp-generation": "sdcpp-generation";
+            "audiogen-ggml": "audiogen-ggml";
             "ggml-vla": "ggml-vla";
             "ggml-classification": "ggml-classification";
             llm: "llm";
@@ -453,6 +548,7 @@ export declare const ttsSupertonicLoadConfigSchema: z.ZodObject<{
     ttsNumInferenceSteps: z.ZodOptional<z.ZodNumber>;
     useGPU: z.ZodOptional<z.ZodBoolean>;
     outputSampleRate: z.ZodOptional<z.ZodNumber>;
+    vulkanCacheDir: z.ZodOptional<z.ZodString>;
     lavasrEnhancerModelSrc: z.ZodOptional<z.ZodUnion<readonly [z.ZodString, z.ZodObject<{
         src: z.ZodString;
         name: z.ZodOptional<z.ZodString>;
@@ -467,6 +563,7 @@ export declare const ttsSupertonicLoadConfigSchema: z.ZodObject<{
         addon: z.ZodOptional<z.ZodUnion<readonly [z.ZodEnum<{
             embeddings: "embeddings";
             diffusion: "diffusion";
+            audiogen: "audiogen";
             tts: "tts";
             ocr: "ocr";
             vla: "vla";
@@ -480,6 +577,7 @@ export declare const ttsSupertonicLoadConfigSchema: z.ZodObject<{
             "parakeet-transcription": "parakeet-transcription";
             "ggml-ocr": "ggml-ocr";
             "sdcpp-generation": "sdcpp-generation";
+            "audiogen-ggml": "audiogen-ggml";
             "ggml-vla": "ggml-vla";
             "ggml-classification": "ggml-classification";
             llm: "llm";
@@ -504,6 +602,7 @@ export declare const ttsSupertonicLoadConfigSchema: z.ZodObject<{
         addon: z.ZodOptional<z.ZodUnion<readonly [z.ZodEnum<{
             embeddings: "embeddings";
             diffusion: "diffusion";
+            audiogen: "audiogen";
             tts: "tts";
             ocr: "ocr";
             vla: "vla";
@@ -517,6 +616,7 @@ export declare const ttsSupertonicLoadConfigSchema: z.ZodObject<{
             "parakeet-transcription": "parakeet-transcription";
             "ggml-ocr": "ggml-ocr";
             "sdcpp-generation": "sdcpp-generation";
+            "audiogen-ggml": "audiogen-ggml";
             "ggml-vla": "ggml-vla";
             "ggml-classification": "ggml-classification";
             llm: "llm";
@@ -528,6 +628,45 @@ export declare const ttsSupertonicLoadConfigSchema: z.ZodObject<{
         }>, z.ZodLiteral<"vad">]>>;
     }, z.core.$strip>]>>;
 }, z.core.$strip>;
+export declare const ttsParlerLoadConfigSchema: z.ZodObject<{
+    useGPU: z.ZodOptional<z.ZodBoolean>;
+    outputSampleRate: z.ZodOptional<z.ZodNumber>;
+    streamChunkTokens: z.ZodOptional<z.ZodNumber>;
+    streamFirstChunkTokens: z.ZodOptional<z.ZodNumber>;
+    threads: z.ZodOptional<z.ZodNumber>;
+    nGpuLayers: z.ZodOptional<z.ZodNumber>;
+    seed: z.ZodOptional<z.ZodNumber>;
+    temperature: z.ZodOptional<z.ZodNumber>;
+    topK: z.ZodOptional<z.ZodNumber>;
+    topP: z.ZodOptional<z.ZodNumber>;
+    maxFrames: z.ZodOptional<z.ZodUnion<readonly [z.ZodLiteral<0>, z.ZodNumber]>>;
+    minNewTokens: z.ZodOptional<z.ZodNumber>;
+    normalizeNumbers: z.ZodOptional<z.ZodBoolean>;
+    description: z.ZodOptional<z.ZodString>;
+    voiceDescription: z.ZodOptional<z.ZodString>;
+    voice: z.ZodOptional<z.ZodString>;
+    emotion: z.ZodOptional<z.ZodEnum<{
+        command: "command";
+        anger: "anger";
+        narration: "narration";
+        conversation: "conversation";
+        disgust: "disgust";
+        fear: "fear";
+        happy: "happy";
+        neutral: "neutral";
+        "proper noun": "proper noun";
+        news: "news";
+        sad: "sad";
+        surprise: "surprise";
+    }>>;
+    pitch: z.ZodOptional<z.ZodString>;
+    pace: z.ZodOptional<z.ZodString>;
+    expressivity: z.ZodOptional<z.ZodString>;
+    noise: z.ZodOptional<z.ZodString>;
+    reverb: z.ZodOptional<z.ZodString>;
+    quality: z.ZodOptional<z.ZodString>;
+    ttsEngine: z.ZodLiteral<"parler">;
+}, z.core.$strip>;
 export declare const ttsLoadConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
     ttsEngine: z.ZodLiteral<"chatterbox">;
     language: z.ZodEnum<{
@@ -560,6 +699,7 @@ export declare const ttsLoadConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
     streamChunkTokens: z.ZodOptional<z.ZodNumber>;
     streamFirstChunkTokens: z.ZodOptional<z.ZodNumber>;
     cfmSteps: z.ZodOptional<z.ZodNumber>;
+    cfgRate: z.ZodOptional<z.ZodNumber>;
     threads: z.ZodOptional<z.ZodNumber>;
     nGpuLayers: z.ZodOptional<z.ZodNumber>;
     seed: z.ZodOptional<z.ZodNumber>;
@@ -577,6 +717,7 @@ export declare const ttsLoadConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
         addon: z.ZodOptional<z.ZodUnion<readonly [z.ZodEnum<{
             embeddings: "embeddings";
             diffusion: "diffusion";
+            audiogen: "audiogen";
             tts: "tts";
             ocr: "ocr";
             vla: "vla";
@@ -590,6 +731,7 @@ export declare const ttsLoadConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
             "parakeet-transcription": "parakeet-transcription";
             "ggml-ocr": "ggml-ocr";
             "sdcpp-generation": "sdcpp-generation";
+            "audiogen-ggml": "audiogen-ggml";
             "ggml-vla": "ggml-vla";
             "ggml-classification": "ggml-classification";
             llm: "llm";
@@ -614,6 +756,7 @@ export declare const ttsLoadConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
         addon: z.ZodOptional<z.ZodUnion<readonly [z.ZodEnum<{
             embeddings: "embeddings";
             diffusion: "diffusion";
+            audiogen: "audiogen";
             tts: "tts";
             ocr: "ocr";
             vla: "vla";
@@ -627,6 +770,7 @@ export declare const ttsLoadConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
             "parakeet-transcription": "parakeet-transcription";
             "ggml-ocr": "ggml-ocr";
             "sdcpp-generation": "sdcpp-generation";
+            "audiogen-ggml": "audiogen-ggml";
             "ggml-vla": "ggml-vla";
             "ggml-classification": "ggml-classification";
             llm: "llm";
@@ -651,6 +795,7 @@ export declare const ttsLoadConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
         addon: z.ZodOptional<z.ZodUnion<readonly [z.ZodEnum<{
             embeddings: "embeddings";
             diffusion: "diffusion";
+            audiogen: "audiogen";
             tts: "tts";
             ocr: "ocr";
             vla: "vla";
@@ -664,6 +809,7 @@ export declare const ttsLoadConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
             "parakeet-transcription": "parakeet-transcription";
             "ggml-ocr": "ggml-ocr";
             "sdcpp-generation": "sdcpp-generation";
+            "audiogen-ggml": "audiogen-ggml";
             "ggml-vla": "ggml-vla";
             "ggml-classification": "ggml-classification";
             llm: "llm";
@@ -688,6 +834,7 @@ export declare const ttsLoadConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
         addon: z.ZodOptional<z.ZodUnion<readonly [z.ZodEnum<{
             embeddings: "embeddings";
             diffusion: "diffusion";
+            audiogen: "audiogen";
             tts: "tts";
             ocr: "ocr";
             vla: "vla";
@@ -701,6 +848,7 @@ export declare const ttsLoadConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
             "parakeet-transcription": "parakeet-transcription";
             "ggml-ocr": "ggml-ocr";
             "sdcpp-generation": "sdcpp-generation";
+            "audiogen-ggml": "audiogen-ggml";
             "ggml-vla": "ggml-vla";
             "ggml-classification": "ggml-classification";
             llm: "llm";
@@ -725,6 +873,7 @@ export declare const ttsLoadConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
         addon: z.ZodOptional<z.ZodUnion<readonly [z.ZodEnum<{
             embeddings: "embeddings";
             diffusion: "diffusion";
+            audiogen: "audiogen";
             tts: "tts";
             ocr: "ocr";
             vla: "vla";
@@ -738,6 +887,7 @@ export declare const ttsLoadConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
             "parakeet-transcription": "parakeet-transcription";
             "ggml-ocr": "ggml-ocr";
             "sdcpp-generation": "sdcpp-generation";
+            "audiogen-ggml": "audiogen-ggml";
             "ggml-vla": "ggml-vla";
             "ggml-classification": "ggml-classification";
             llm: "llm";
@@ -762,6 +912,7 @@ export declare const ttsLoadConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
         addon: z.ZodOptional<z.ZodUnion<readonly [z.ZodEnum<{
             embeddings: "embeddings";
             diffusion: "diffusion";
+            audiogen: "audiogen";
             tts: "tts";
             ocr: "ocr";
             vla: "vla";
@@ -775,6 +926,7 @@ export declare const ttsLoadConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
             "parakeet-transcription": "parakeet-transcription";
             "ggml-ocr": "ggml-ocr";
             "sdcpp-generation": "sdcpp-generation";
+            "audiogen-ggml": "audiogen-ggml";
             "ggml-vla": "ggml-vla";
             "ggml-classification": "ggml-classification";
             llm: "llm";
@@ -825,6 +977,7 @@ export declare const ttsLoadConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
     ttsNumInferenceSteps: z.ZodOptional<z.ZodNumber>;
     useGPU: z.ZodOptional<z.ZodBoolean>;
     outputSampleRate: z.ZodOptional<z.ZodNumber>;
+    vulkanCacheDir: z.ZodOptional<z.ZodString>;
     lavasrEnhancerModelSrc: z.ZodOptional<z.ZodUnion<readonly [z.ZodString, z.ZodObject<{
         src: z.ZodString;
         name: z.ZodOptional<z.ZodString>;
@@ -839,6 +992,7 @@ export declare const ttsLoadConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
         addon: z.ZodOptional<z.ZodUnion<readonly [z.ZodEnum<{
             embeddings: "embeddings";
             diffusion: "diffusion";
+            audiogen: "audiogen";
             tts: "tts";
             ocr: "ocr";
             vla: "vla";
@@ -852,6 +1006,7 @@ export declare const ttsLoadConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
             "parakeet-transcription": "parakeet-transcription";
             "ggml-ocr": "ggml-ocr";
             "sdcpp-generation": "sdcpp-generation";
+            "audiogen-ggml": "audiogen-ggml";
             "ggml-vla": "ggml-vla";
             "ggml-classification": "ggml-classification";
             llm: "llm";
@@ -876,6 +1031,7 @@ export declare const ttsLoadConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
         addon: z.ZodOptional<z.ZodUnion<readonly [z.ZodEnum<{
             embeddings: "embeddings";
             diffusion: "diffusion";
+            audiogen: "audiogen";
             tts: "tts";
             ocr: "ocr";
             vla: "vla";
@@ -889,6 +1045,7 @@ export declare const ttsLoadConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
             "parakeet-transcription": "parakeet-transcription";
             "ggml-ocr": "ggml-ocr";
             "sdcpp-generation": "sdcpp-generation";
+            "audiogen-ggml": "audiogen-ggml";
             "ggml-vla": "ggml-vla";
             "ggml-classification": "ggml-classification";
             llm: "llm";
@@ -899,14 +1056,113 @@ export declare const ttsLoadConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
             classification: "classification";
         }>, z.ZodLiteral<"vad">]>>;
     }, z.core.$strip>]>>;
+}, z.core.$strip>, z.ZodObject<{
+    useGPU: z.ZodOptional<z.ZodBoolean>;
+    outputSampleRate: z.ZodOptional<z.ZodNumber>;
+    streamChunkTokens: z.ZodOptional<z.ZodNumber>;
+    streamFirstChunkTokens: z.ZodOptional<z.ZodNumber>;
+    threads: z.ZodOptional<z.ZodNumber>;
+    nGpuLayers: z.ZodOptional<z.ZodNumber>;
+    seed: z.ZodOptional<z.ZodNumber>;
+    temperature: z.ZodOptional<z.ZodNumber>;
+    topK: z.ZodOptional<z.ZodNumber>;
+    topP: z.ZodOptional<z.ZodNumber>;
+    maxFrames: z.ZodOptional<z.ZodUnion<readonly [z.ZodLiteral<0>, z.ZodNumber]>>;
+    minNewTokens: z.ZodOptional<z.ZodNumber>;
+    normalizeNumbers: z.ZodOptional<z.ZodBoolean>;
+    description: z.ZodOptional<z.ZodString>;
+    voiceDescription: z.ZodOptional<z.ZodString>;
+    voice: z.ZodOptional<z.ZodString>;
+    emotion: z.ZodOptional<z.ZodEnum<{
+        command: "command";
+        anger: "anger";
+        narration: "narration";
+        conversation: "conversation";
+        disgust: "disgust";
+        fear: "fear";
+        happy: "happy";
+        neutral: "neutral";
+        "proper noun": "proper noun";
+        news: "news";
+        sad: "sad";
+        surprise: "surprise";
+    }>>;
+    pitch: z.ZodOptional<z.ZodString>;
+    pace: z.ZodOptional<z.ZodString>;
+    expressivity: z.ZodOptional<z.ZodString>;
+    noise: z.ZodOptional<z.ZodString>;
+    reverb: z.ZodOptional<z.ZodString>;
+    quality: z.ZodOptional<z.ZodString>;
+    ttsEngine: z.ZodLiteral<"parler">;
 }, z.core.$strip>], "ttsEngine">;
 export declare const LEGACY_TTS_ONNX_MODEL_CONFIG_FIELDS: readonly ["ttsSupertonicMultilingual", "ttsTokenizerSrc", "ttsSpeechEncoderSrc", "ttsEmbedTokensSrc", "ttsConditionalDecoderSrc", "ttsLanguageModelSrc", "ttsTextEncoderSrc", "ttsDurationPredictorSrc", "ttsVectorEstimatorSrc", "ttsVocoderSrc", "ttsUnicodeIndexerSrc", "ttsTtsConfigSrc", "ttsVoiceStyleSrc"];
 export declare const ttsConfigSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
     [x: string]: z.ZodOptional<z.ZodUnknown>;
 }, z.core.$strict>, z.ZodObject<{
     [x: string]: z.ZodOptional<z.ZodUnknown>;
+}, z.core.$strict>, z.ZodObject<{
+    useGPU: z.ZodOptional<z.ZodBoolean>;
+    outputSampleRate: z.ZodOptional<z.ZodNumber>;
+    streamChunkTokens: z.ZodOptional<z.ZodNumber>;
+    streamFirstChunkTokens: z.ZodOptional<z.ZodNumber>;
+    threads: z.ZodOptional<z.ZodNumber>;
+    nGpuLayers: z.ZodOptional<z.ZodNumber>;
+    seed: z.ZodOptional<z.ZodNumber>;
+    temperature: z.ZodOptional<z.ZodNumber>;
+    topK: z.ZodOptional<z.ZodNumber>;
+    topP: z.ZodOptional<z.ZodNumber>;
+    maxFrames: z.ZodOptional<z.ZodUnion<readonly [z.ZodLiteral<0>, z.ZodNumber]>>;
+    minNewTokens: z.ZodOptional<z.ZodNumber>;
+    normalizeNumbers: z.ZodOptional<z.ZodBoolean>;
+    description: z.ZodOptional<z.ZodString>;
+    voiceDescription: z.ZodOptional<z.ZodString>;
+    voice: z.ZodOptional<z.ZodString>;
+    emotion: z.ZodOptional<z.ZodEnum<{
+        command: "command";
+        anger: "anger";
+        narration: "narration";
+        conversation: "conversation";
+        disgust: "disgust";
+        fear: "fear";
+        happy: "happy";
+        neutral: "neutral";
+        "proper noun": "proper noun";
+        news: "news";
+        sad: "sad";
+        surprise: "surprise";
+    }>>;
+    pitch: z.ZodOptional<z.ZodString>;
+    pace: z.ZodOptional<z.ZodString>;
+    expressivity: z.ZodOptional<z.ZodString>;
+    noise: z.ZodOptional<z.ZodString>;
+    reverb: z.ZodOptional<z.ZodString>;
+    quality: z.ZodOptional<z.ZodString>;
+    ttsEngine: z.ZodLiteral<"parler">;
 }, z.core.$strict>], "ttsEngine">;
 export declare const ttsClientParamsSchema: z.ZodObject<{
+    description: z.ZodOptional<z.ZodString>;
+    voiceDescription: z.ZodOptional<z.ZodString>;
+    voice: z.ZodOptional<z.ZodString>;
+    emotion: z.ZodOptional<z.ZodEnum<{
+        command: "command";
+        anger: "anger";
+        narration: "narration";
+        conversation: "conversation";
+        disgust: "disgust";
+        fear: "fear";
+        happy: "happy";
+        neutral: "neutral";
+        "proper noun": "proper noun";
+        news: "news";
+        sad: "sad";
+        surprise: "surprise";
+    }>>;
+    pitch: z.ZodOptional<z.ZodString>;
+    pace: z.ZodOptional<z.ZodString>;
+    expressivity: z.ZodOptional<z.ZodString>;
+    noise: z.ZodOptional<z.ZodString>;
+    reverb: z.ZodOptional<z.ZodString>;
+    quality: z.ZodOptional<z.ZodString>;
     modelId: z.ZodString;
     inputType: z.ZodDefault<z.ZodString>;
     text: z.ZodString;
@@ -916,6 +1172,30 @@ export declare const ttsClientParamsSchema: z.ZodObject<{
     sentenceStreamMaxChunkScalars: z.ZodOptional<z.ZodNumber>;
 }, z.core.$strip>;
 export declare const ttsRequestSchema: z.ZodObject<{
+    type: z.ZodLiteral<"textToSpeech">;
+    description: z.ZodOptional<z.ZodString>;
+    voiceDescription: z.ZodOptional<z.ZodString>;
+    voice: z.ZodOptional<z.ZodString>;
+    emotion: z.ZodOptional<z.ZodEnum<{
+        command: "command";
+        anger: "anger";
+        narration: "narration";
+        conversation: "conversation";
+        disgust: "disgust";
+        fear: "fear";
+        happy: "happy";
+        neutral: "neutral";
+        "proper noun": "proper noun";
+        news: "news";
+        sad: "sad";
+        surprise: "surprise";
+    }>>;
+    pitch: z.ZodOptional<z.ZodString>;
+    pace: z.ZodOptional<z.ZodString>;
+    expressivity: z.ZodOptional<z.ZodString>;
+    noise: z.ZodOptional<z.ZodString>;
+    reverb: z.ZodOptional<z.ZodString>;
+    quality: z.ZodOptional<z.ZodString>;
     modelId: z.ZodString;
     inputType: z.ZodDefault<z.ZodString>;
     text: z.ZodString;
@@ -923,11 +1203,12 @@ export declare const ttsRequestSchema: z.ZodObject<{
     sentenceStream: z.ZodDefault<z.ZodBoolean>;
     sentenceStreamLocale: z.ZodOptional<z.ZodString>;
     sentenceStreamMaxChunkScalars: z.ZodOptional<z.ZodNumber>;
-    type: z.ZodLiteral<"textToSpeech">;
 }, z.core.$strip>;
 export declare const ttsStatsSchema: z.ZodObject<{
     audioDuration: z.ZodOptional<z.ZodNumber>;
     totalSamples: z.ZodOptional<z.ZodNumber>;
+    enhancerBackendDevice: z.ZodOptional<z.ZodNumber>;
+    enhancerBackendId: z.ZodOptional<z.ZodNumber>;
 }, z.core.$strip>;
 export declare const ttsResponseSchema: z.ZodObject<{
     type: z.ZodLiteral<"textToSpeech">;
@@ -936,11 +1217,36 @@ export declare const ttsResponseSchema: z.ZodObject<{
     stats: z.ZodOptional<z.ZodObject<{
         audioDuration: z.ZodOptional<z.ZodNumber>;
         totalSamples: z.ZodOptional<z.ZodNumber>;
+        enhancerBackendDevice: z.ZodOptional<z.ZodNumber>;
+        enhancerBackendId: z.ZodOptional<z.ZodNumber>;
     }, z.core.$strip>>;
     chunkIndex: z.ZodOptional<z.ZodNumber>;
     sentenceChunk: z.ZodOptional<z.ZodString>;
 }, z.core.$strip>;
-declare const textToSpeechStreamRequestBaseSchema: z.ZodObject<{
+declare const textToSpeechStreamRequestBaseShape: {
+    description: z.ZodOptional<z.ZodString>;
+    voiceDescription: z.ZodOptional<z.ZodString>;
+    voice: z.ZodOptional<z.ZodString>;
+    emotion: z.ZodOptional<z.ZodEnum<{
+        command: "command";
+        anger: "anger";
+        narration: "narration";
+        conversation: "conversation";
+        disgust: "disgust";
+        fear: "fear";
+        happy: "happy";
+        neutral: "neutral";
+        "proper noun": "proper noun";
+        news: "news";
+        sad: "sad";
+        surprise: "surprise";
+    }>>;
+    pitch: z.ZodOptional<z.ZodString>;
+    pace: z.ZodOptional<z.ZodString>;
+    expressivity: z.ZodOptional<z.ZodString>;
+    noise: z.ZodOptional<z.ZodString>;
+    reverb: z.ZodOptional<z.ZodString>;
+    quality: z.ZodOptional<z.ZodString>;
     modelId: z.ZodString;
     inputType: z.ZodDefault<z.ZodString>;
     accumulateSentences: z.ZodOptional<z.ZodBoolean>;
@@ -951,8 +1257,32 @@ declare const textToSpeechStreamRequestBaseSchema: z.ZodObject<{
     }>>;
     maxBufferScalars: z.ZodOptional<z.ZodNumber>;
     flushAfterMs: z.ZodOptional<z.ZodNumber>;
-}, z.core.$strip>;
+};
 export declare const textToSpeechStreamRequestSchema: z.ZodObject<{
+    type: z.ZodLiteral<"textToSpeechStream">;
+    description: z.ZodOptional<z.ZodString>;
+    voiceDescription: z.ZodOptional<z.ZodString>;
+    voice: z.ZodOptional<z.ZodString>;
+    emotion: z.ZodOptional<z.ZodEnum<{
+        command: "command";
+        anger: "anger";
+        narration: "narration";
+        conversation: "conversation";
+        disgust: "disgust";
+        fear: "fear";
+        happy: "happy";
+        neutral: "neutral";
+        "proper noun": "proper noun";
+        news: "news";
+        sad: "sad";
+        surprise: "surprise";
+    }>>;
+    pitch: z.ZodOptional<z.ZodString>;
+    pace: z.ZodOptional<z.ZodString>;
+    expressivity: z.ZodOptional<z.ZodString>;
+    noise: z.ZodOptional<z.ZodString>;
+    reverb: z.ZodOptional<z.ZodString>;
+    quality: z.ZodOptional<z.ZodString>;
     modelId: z.ZodString;
     inputType: z.ZodDefault<z.ZodString>;
     accumulateSentences: z.ZodOptional<z.ZodBoolean>;
@@ -963,7 +1293,6 @@ export declare const textToSpeechStreamRequestSchema: z.ZodObject<{
     }>>;
     maxBufferScalars: z.ZodOptional<z.ZodNumber>;
     flushAfterMs: z.ZodOptional<z.ZodNumber>;
-    type: z.ZodLiteral<"textToSpeechStream">;
 }, z.core.$strip>;
 export declare const textToSpeechStreamResponseSchema: z.ZodObject<{
     type: z.ZodLiteral<"textToSpeechStream">;
@@ -972,6 +1301,8 @@ export declare const textToSpeechStreamResponseSchema: z.ZodObject<{
     stats: z.ZodOptional<z.ZodObject<{
         audioDuration: z.ZodOptional<z.ZodNumber>;
         totalSamples: z.ZodOptional<z.ZodNumber>;
+        enhancerBackendDevice: z.ZodOptional<z.ZodNumber>;
+        enhancerBackendId: z.ZodOptional<z.ZodNumber>;
     }, z.core.$strip>>;
     chunkIndex: z.ZodOptional<z.ZodNumber>;
     sentenceChunk: z.ZodOptional<z.ZodString>;
@@ -979,8 +1310,10 @@ export declare const textToSpeechStreamResponseSchema: z.ZodObject<{
 export type TtsLanguage = (typeof TTS_LANGUAGES)[number];
 export type TtsChatterboxLanguage = (typeof TTS_CHATTERBOX_LANGUAGES)[number];
 export type TtsSupertonicLanguage = (typeof TTS_SUPERTONIC_LANGUAGES)[number];
+export type TtsParlerEmotion = (typeof TTS_PARLER_EMOTIONS)[number];
 export type TtsChatterboxLoadConfig = z.infer<typeof ttsChatterboxLoadConfigSchema>;
 export type TtsSupertonicLoadConfig = z.infer<typeof ttsSupertonicLoadConfigSchema>;
+export type TtsParlerLoadConfig = z.infer<typeof ttsParlerLoadConfigSchema>;
 export type TtsLoadConfig = z.infer<typeof ttsLoadConfigSchema>;
 /** @deprecated Use {@link TtsChatterboxLoadConfig} */
 export type TtsChatterboxConfig = TtsChatterboxLoadConfig;
@@ -988,6 +1321,7 @@ export type TtsChatterboxConfig = TtsChatterboxLoadConfig;
 export type TtsSupertonicConfig = TtsSupertonicLoadConfig;
 export type TtsChatterboxRuntimeConfig = z.infer<typeof ttsChatterboxRuntimeConfigSchema>;
 export type TtsSupertonicRuntimeConfig = z.infer<typeof ttsSupertonicRuntimeConfigSchema>;
+export type TtsParlerRuntimeConfig = z.infer<typeof ttsParlerRuntimeConfigSchema>;
 export type TtsRuntimeConfig = z.infer<typeof ttsRuntimeConfigSchema>;
 export type TtsConfig = z.infer<typeof ttsConfigSchema>;
 export type TtsClientParamsInput = z.input<typeof ttsClientParamsSchema>;
@@ -1002,7 +1336,7 @@ export type TtsSentenceChunkUpdate = {
 };
 export type TextToSpeechStreamRequest = z.infer<typeof textToSpeechStreamRequestSchema>;
 export type TextToSpeechStreamResponse = z.infer<typeof textToSpeechStreamResponseSchema>;
-export type TextToSpeechStreamClientParams = z.infer<typeof textToSpeechStreamRequestBaseSchema>;
+export type TextToSpeechStreamClientParams = z.output<z.ZodObject<typeof textToSpeechStreamRequestBaseShape>>;
 export interface TextToSpeechStreamResult {
     bufferStream: AsyncGenerator<number>;
     chunkUpdates?: AsyncGenerator<TtsSentenceChunkUpdate>;
@@ -1010,7 +1344,7 @@ export interface TextToSpeechStreamResult {
     done: Promise<boolean>;
 }
 export interface TextToSpeechStreamSession {
-    write(textFragment: string | Buffer): void;
+    write(textFragment: string | Uint8Array): void;
     end(): void;
     destroy(): void;
     [Symbol.asyncIterator](): AsyncIterator<TextToSpeechStreamResponse>;