arcane-os 0.93.0 → 0.95.0

package/docs/reference/sdk-api.md

@@ -82,6 +82,7 @@ runtime layouts.
 | `arcane-os/core/image` | Native image Core service with independent runtime preparation and retained model ownership. |
 | `arcane-os/core/speech` | Independent injected STT/TTS engine loading, request cancellation and joined Core service lifetime. |
 | `arcane-os/local-ai/whisper` | Retained native Whisper model, complete recordings and joined helper lifetime. |
+| `arcane-os/local-ai/kokoro` | Retained native Kokoro synthesis using the existing ONNX/model-resource owners and a compiled phonemization/Opus helper. |
 | `arcane-os/local-ai/whisper/build` | First-party persistent helper build against selected installed Whisper headers and libraries. |
 | `arcane-os/local-ai/whisper/openvino-build` | Optional Windows x64 Intel NPU encoder runtime producer using selected installed sources and toolchain. |
 | `arcane-os/ai/core-model-assets` | Complete stored browser model members projected through Core into native working files. |
@@ -469,6 +470,12 @@ The remaining data-only subpaths are eight JSON Schemas and package metadata.
 | `createLocalImageService()` | function | `arcane-os/core/image` | Core local images | Node Core with selected stable-diffusion.cpp requirements |
 | `createLocalImageService default export` | function | `arcane-os/core/image` | Core local images | Same native image service factory |
 | `createSpeechService()` | function | `arcane-os/core/speech` | Core native speech | Node Core with explicitly supplied speech engines |
+| `createNativeKokoroRuntime()` | function | `arcane-os/local-ai/kokoro` | Core native speech | Node with matching prepared helper/data, selected model resources and an existing ONNX owner |
+| `createNativeKokoroRuntime default export` | function | `arcane-os/local-ai/kokoro` | Core native speech | Same retained native Kokoro factory |
+| `KOKORO_MODEL` | constant | `arcane-os/local-ai/kokoro` | Core native speech | Selected upstream model identifier |
+| `KOKORO_REVISION` | constant | `arcane-os/local-ai/kokoro` | Core native speech | Selected upstream model revision |
+| `KOKORO_SAMPLE_RATE` | constant | `arcane-os/local-ai/kokoro` | Core native speech | Native PCM sample rate |
+| `KOKORO_VOICES` | constant | `arcane-os/local-ai/kokoro` | Core native speech | Complete 28-voice US/GB selection |
 | `createWhisperRuntime()` | function | `arcane-os/local-ai/whisper` | Core native speech | Node with a prepared matching helper, runtime, decoder and selected model |
 | `createWhisperRuntime default export` | function | `arcane-os/local-ai/whisper` | Core native speech | Same retained native engine factory |
 | `buildWhisperHelper()` | function | `arcane-os/local-ai/whisper/build` | Core native speech | Node with installed CMake/C++17 toolchain and matching Whisper source/runtime |
@@ -8842,6 +8849,118 @@ selected model and native engine.
 The default export from `arcane-os/core/image` is the same
 `createLocalImageService` factory and lifecycle described above.
 
+## createNativeKokoroRuntime()
+
+### Overview and signature
+
+The named export from `arcane-os/local-ai/kokoro` composes the selected Kokoro
+FP32 graph with the host's existing native ONNX owner, model-resource owner
+and prepared persistent phonemization/Opus helper. Construction starts no
+native work and acquires no model or runtime.
+
+```javascript
+createNativeKokoroRuntime({
+    onnx, modelAssets, runtime, prepare, modelId = 'kokoro',
+    model = KOKORO_MODEL, revision = KOKORO_REVISION, dtype = 'fp32',
+    paths, assetProjectionId, resourcePaths, sessionOptions,
+    executionPreference = 'gpu', executionTarget, signal, onEvent
+} = {})
+```
+
+Supply the existing `onnx` runtime or a `prepare` callback that provides it.
+`runtime` describes the matching native helper and data. `paths` supplies
+complete prepared graph/tokenizer/voice resources; a completed
+`assetProjectionId` instead retains projected resources through `modelAssets`.
+The selected model/revision/FP32 contract is fixed by this frontend.
+See [native Kokoro](native-speech.md) for exact resource mappings, preparation,
+runtime distribution and model ownership.
+
+### Members and results
+
+- `current()` returns complete model/lifecycle state, execution configuration,
+  current request, queue, progress, error, default voice and supported voices.
+- `subscribe(listener,{replay=true,signal}={})` returns an unsubscribe function
+  and replays current state by default.
+- `load(options={})` activates the selected resources, retaining omitted
+  selections. Explicit projection/resource mapping or execution-target changes
+  join prior native retirement before loading the new activation.
+- `synthesize(request,{signal,onProgress,requestId=null}={})` requires a loaded
+  activation. `request` contains the complete `input` string, optional `model`
+  matching `modelId`, `voice` (default `af_heart`), positive finite `speed`
+  (default `1`) and `responseFormat` (`wav` by default, `opus` or `ogg`).
+  The result is `{audioBase64,contentType,sampleRate,channels,model,voice,speed}`;
+  content type is `audio/wav` or `audio/ogg; codecs=opus`, with mono 24kHz PCM
+  synthesis. The full input is processed in ordered model segments.
+- `unload()` retires the activation and joins owned native work. `close()`
+  permanently closes the engine and releases its state subscriptions.
+
+Queued requests retain order. Cancelling a queued request removes only that
+request. Active cancellation waits for actual helper/session retirement;
+surviving requests resume with the same accepted provider configuration.
+The ONNX owner may need a running native call to return before its worker exits.
+Readiness is lost while that retirement/reload occurs. Errors retain the actual
+engine and cleanup failures; unsupported explicit voices or formats are never
+substituted. No audio is played by this engine.
+
+### Example
+
+```javascript
+import {createNativeKokoroRuntime} from 'arcane-os/local-ai/kokoro';
+
+// The host supplies its existing ONNX owner and already prepared resources.
+async function narrateMoonGoat({onnx, runtime, paths}) {
+    const voice = createNativeKokoroRuntime({
+        onnx, runtime, paths, executionPreference: 'cpu'
+    });
+    try {
+        await voice.load();
+        return await voice.synthesize({
+            input: 'Captain Goat has landed. Guard the moon cheese!',
+            voice: 'af_heart', responseFormat: 'wav'
+        });
+    } finally {
+        await voice.close();
+    }
+}
+```
+
+Changing `voice` to `bf_emma` selects British English. `responseFormat: 'opus'`
+selects Ogg Opus encoding. GPU/physical-device selection uses the existing
+[ONNX execution contract](local-ai.md#physical-execution-targets); an accepted
+provider configuration is separate from observed hardware execution.
+The SDK publishes a Windows x64 helper archive. Other platforms need a matching
+custom helper distribution and supported native ONNX host. Native helper
+production and platform execution evidence remain separate.
+
+## createNativeKokoroRuntime default export
+
+The default export from `arcane-os/local-ai/kokoro` is the same
+`createNativeKokoroRuntime` factory with identical inputs, results and lifetime.
+
+## KOKORO_MODEL
+
+Named string export from `arcane-os/local-ai/kokoro`, with value
+`onnx-community/Kokoro-82M-v1.0-ONNX`. It identifies this frontend's model family
+for matching graph, tokenizer and voice resource selection.
+
+## KOKORO_REVISION
+
+Named string export from `arcane-os/local-ai/kokoro`, with value
+`1939ad2a8e416c0acfeecc08a694d14ef25f2231`. Resource preparation uses this
+upstream revision with `KOKORO_MODEL`.
+
+## KOKORO_SAMPLE_RATE
+
+Named number export from `arcane-os/local-ai/kokoro`, with value `24000`.
+It describes the engine's mono PCM synthesis rate in samples per second.
+
+## KOKORO_VOICES
+
+Named array export from `arcane-os/local-ai/kokoro` containing all 28 supported
+US/GB voice identifiers. The engine uses `af_heart` when the caller omits
+`voice`; an explicit unsupported selection reports an error. Use this complete
+array to populate a native Kokoro voice selector.
+
 ## createWhisperRuntime()
 
 ### Overview
@@ -9018,6 +9137,13 @@ The returned object has `name: 'speech'`, `current`, `subscribe`, `close`,
   Core RPC methods. The context supplies `signal`, `requestId` and `emit`.
   The service publishes synchronous accepted `Thinking` before waiting for
   its role's load, then forwards the engine's complete progress and result.
+- `methods['speech.load'](request,context)` and
+  `methods['speech.unload'](request,context)` route explicit activation to the
+  explicit `role: 'stt' | 'tts'` and forward the remaining activation
+  fields and result through that role's configured engine. A startup load remains owned independently of callers
+  waiting for it. The browser facade exposes `Arcane.speech.load(request,options)`
+  and `unload(request,options)` with `signal`, `onRequest` and no elapsed-time
+  cutoff. See [activation routing](native-speech.md) for selection and errors.
 - `close()` and its `drain()` alias stop acceptance, abort the service lifetime,
   close both engines concurrently and await startup and request work. Repeated
   calls share one promise. `dispose()` also releases event subscriptions.
@@ -9123,7 +9249,8 @@ import createLocalAIService from 'arcane-os/core/local-ai';
 ### Overview
 
 Reuses matching managed runtimes or installs complete selected
-llama.cpp/Ollama/ONNX/image distributions or NeMo libraries in an explicitly supplied directory.
+llama.cpp/Ollama/ONNX/image distributions, NeMo libraries or native Kokoro
+helper/data trees in an explicitly supplied directory.
 
 ### Signature and result
 
@@ -9146,6 +9273,12 @@ trees remain intact while a fresh installation is prepared. See
 Image requirements also accept `backend` and
 `models`; their pinned default runtime, CPU/Metal selection and separate model
 preparation are described in [local image generation](local-image-generation.md).
+`kokoro-native` returns `helperExecutable`, `espeakDataDirectory` and
+`libraryDirectory`. Windows x64 defaults to the helper archive from the
+installed SDK's numeric release; an explicit `url` or `helperRoot` selects a
+complete custom distribution. The data directory is the parent of
+`espeak-ng-data`. Helper preparation loads no Kokoro graph and keeps the
+existing ONNX/model-resource owners separate. See [native speech](native-speech.md).
 Matching concurrent
 installs share their work. Downloads retain runtime libraries and surface
 network/archive failures; cancellation and operation events remain observable.
@@ -9189,6 +9322,10 @@ The corrected Windows x64 ONNX selection retains its
 is relocated with the other runtime paths; bundling introduces no separate
 runtime selection. See [ONNX runtime preparation](local-ai.md#development).
 
+Kokoro bundling retains the complete helper/data tree and relocates
+`helperExecutable`, `espeakDataDirectory` and `libraryDirectory`. Its selected
+ONNX runtime and model resources retain their existing independent ownership.
+
 Image records relocate the complete library, binding and variant paths. Model
 URL descriptors retain their original acquisition metadata for preparation
 after launch. Runtime-contained native model paths become artifact-relative;
@@ -11683,10 +11820,11 @@ the message or response callback payload.
 
 **Node and Browser; Cloud transport.** Uses standard Fetch and cancellation,
 without DOM, browser profiles, user singletons, or storage initialization.
-Import starts no request. HTTP `429` whose message contains `overload`
-(case-insensitive) waits
-`3000` milliseconds and retries the complete request; other HTTP failures
-throw their complete parsed JSON or text bodies. A missing key throws
+Import starts no request. Rejected Fetch and all HTTP `429`/`529` share three
+retries. Quota recovery honors `Retry-After`, otherwise waits `3000`, `6000`,
+or `12000` milliseconds by retry number. Active same-endpoint/credential calls
+share quota cooldown and paced dispatch. Complete error bodies remain unchanged
+on exhaustion; other HTTP failures are not retried. A missing key throws
 `AI_PROVIDER_NOT_CONFIGURED`; a missing model throws `TypeError`. `signal`
 cancellation during transport, body reading, retry waiting,
 or callback settlement prevents successful return and uses
@@ -11836,21 +11974,24 @@ Ordinary TWiN callers use `fetchRequest()` instead.
 ### Signature and result
 
 ```text
-async fetchHTTPResponse(url,options)
+async fetchHTTPResponse(url,options,{onRetry=null}={})
 ```
 
 Returns the successful Fetch `Response` without consuming its body. Both URL
 and Fetch options are caller-supplied; this helper adds no key, model, or
 request envelope. Non-success responses are read completely as JSON when the
-content type contains `application/json`, otherwise as text. Only status 429
-with an overload message repeats after 3000 ms; other error bodies are thrown.
+content type contains `application/json`, otherwise as text. Rejected Fetch
+and all `429`/`529` share three retries with complete terminal errors.
+`429` honors `Retry-After` or exponential delay and coordinates a transient
+same-endpoint/credential cooldown. See [shared request behavior](ai/twin-cloud.md#shared-request-behavior).
 
 ### Availability and normalization
 
 **Node and Browser.** Exported from `arcane-os/ai/twin-cloud` for shared SDK
-integration. `options.signal` cancels Fetch and the overload wait and is checked
+integration. `options.signal` cancels Fetch and recovery/pacing waits and is checked
 after response/error-body reads. Cancellation uses
-`ARCANE_AI_REQUEST_ABORTED`. Overload warnings use the existing shared logger.
+`ARCANE_AI_REQUEST_ABORTED`. Retry warnings use the existing shared logger;
+`onRetry` observes complete waiting/requesting records outside the payload.
 
 ### Example
 
@@ -11870,7 +12011,7 @@ Shared complete JSON-body reader built on `fetchHTTPResponse()`.
 ### Signature and result
 
 ```text
-async fetchJSONResponse(url,options)
+async fetchJSONResponse(url,options,{onRetry=null}={})
 ```
 
 Returns the full parsed JSON value. A successful response whose content type

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "arcane-os",
-  "version": "0.93.0",
+  "version": "0.95.0",
   "description": "Arcane OS JavaScript SDK, project-local CLI, browser runtime, and repository-portable application packager.",
   "type": "module",
   "main": "./src/index.mjs",
@@ -89,6 +89,11 @@
     "./local-ai/decisions": "./src/local-ai/decisions.mjs",
     "./local-ai/image": "./src/local-ai/image-runtime.mjs",
     "./local-ai/whisper": "./src/local-ai/whisper/index.mjs",
+    "./local-ai/kokoro": "./src/local-ai/kokoro/index.mjs",
+    "./local-ai/nemotron": "./src/local-ai/nemotron/index.mjs",
+    "./local-ai/nemotron/build": "./src/local-ai/nemotron/build.mjs",
+    "./local-ai/magpie": "./src/local-ai/magpie/index.mjs",
+    "./local-ai/magpie/build": "./src/local-ai/magpie/build.mjs",
     "./local-ai/whisper/build": "./src/local-ai/whisper/build.mjs",
     "./local-ai/whisper/openvino-build": "./src/local-ai/whisper/openvino-build.mjs",
     "./integrated-provider": "./src/integrated-provider-loader.mjs",

package/runtime/arcane/modules/AI.js

@@ -28,6 +28,8 @@ import {
 import {MarkdownSpeech,stripSpeechFormatting} from 'arcane-os/speech-text';
 import {prepareSpeech, readPreparedSpeech} from './PreparedSpeech.js';
 import {createToolTextObserver} from 'arcane-os/ai/tool-text-stream';
+import createNativeSpeechCapture from './NativeSpeechCapture.js';
+import prepareNativeSpeechPlayback from './NativeSpeechPlayback.js';
 
 const completeValue=(value)=>value;
 
@@ -1150,14 +1152,18 @@ class AI {
             }
         );
 
+        const speechOnly=llmService===null&&model===null;
         const preferences=[
-            llmService||'TWIN',
+            speechOnly?'':llmService||'TWIN',
             sttService||'LOCAL_SPEACH',
             ttsService||'LOCAL_SPEACH',
-            model||'TWIN',
+            speechOnly?'':model||'TWIN',
             modelTTS||'LOCAL_SPEACH',
             modelSTT||'LOCAL_SPEACH'
         ];
+        // Explicitly absent LLM selection must not briefly register or load a
+        // default provider. setAI retains empty entries from this initial tuple.
+        if(speechOnly)this.#preferenceTuple=preferences.slice();
         this.setAI(
             ...preferences
         );
@@ -2008,13 +2014,15 @@ class AI {
                 if(runtime.#builtInSpeechService(role)!==providerId||!model){
                     return completeValue([]);
                 }
-                const defaultVoice=runtime.#builtInSpeechDefaultVoice(
+                const defaultVoice=nativeWatch?.snapshot?.roles?.[role]?.defaultVoice??runtime.#builtInSpeechDefaultVoice(
                     role,
                     providerId
                 );
                 return completeValue([
                     completeValue({
                         id:model,
+                        ...(nativeWatch?.snapshot?.roles?.[role]?.speech
+                            ?{speech:nativeWatch.snapshot.roles[role].speech}:{}),
                         ...(defaultVoice?{defaultVoice}:{})
                     })
                 ]);
@@ -2026,6 +2034,39 @@ class AI {
                 return runtime.#builtInSpeechInspection(role,providerId,selection);
             },
             status:statusBuiltInSpeechProvider,
+            ...(role==='stt'?{
+                supportsCapture:function supportsNativeCapture(){
+                    return nativeWatch?.snapshot?.roles?.stt?.supportsStreaming===true;
+                },
+                createCapture:function createBuiltInNativeCapture(options={}){
+                    if(nativeWatch?.snapshot?.roles?.stt?.supportsStreaming!==true)return null;
+                    const capture=createNativeSpeechCapture({
+                        ...options,
+                        speech:nativeWatch.speech,
+                        model:nativeWatch.modelId
+                    });
+                    const operation={watch:nativeWatch,requestId:null,signal:null};
+                    const done=capture.done.finally(function releaseNativeCapture(){
+                        if(nativeRequest===operation)releaseBuiltInSpeechRequest();
+                    });
+                    done.catch(function observeNativeCaptureCompletion(error){
+                        if(!isAIRequestAbort(error))arcaneLogging.error('Native transcription capture failed.',error);
+                    });
+                    return {
+                        ...capture,
+                        done,
+                        start:function startBuiltInNativeCapture(options={}){
+                            if(!nativeSpeechReady()||busy){
+                                throw aiProviderError('The native transcription model is not ready.','ARCANE_AI_ROLE_NOT_READY');
+                            }
+                            busy=true;
+                            operation.signal=options.signal;
+                            nativeRequest=operation;
+                            return capture.start(options);
+                        }
+                    };
+                }
+            }:{}),
             load:async function loadBuiltInSpeechProvider(context={}){
                 if(context.signal?.aborted){
                     throw normalizeAIRequestAbort(context.signal.reason);
@@ -2086,7 +2127,7 @@ class AI {
                     throw error;
                 }
             },
-            request:function requestBuiltInSpeechProvider(context={}){
+            request:function requestBuiltInSpeechProvider(context={}, {speechStream=null}={}){
                 if(context.signal?.aborted){
                     throw normalizeAIRequestAbort(context.signal.reason);
                 }
@@ -2126,7 +2167,8 @@ class AI {
                     )
                     :runtime.#requestBuiltInSpeechSynthesis(
                         context.payload,
-                        context.signal
+                        context.signal,
+                        speechStream
                     );
                 return Promise.resolve(request).finally(releaseBuiltInSpeechRequest);
             },
@@ -2548,6 +2590,7 @@ class AI {
 
     audioMessageChunks='';
     #markdownSpeech=new MarkdownSpeech();
+    #streamSpeechOptions=null;
     sourceNodes=[];
     isSpeaking=false;
     audioContext=null;
@@ -4684,7 +4727,7 @@ class AI {
         return response.text();
     }
 
-    async #requestBuiltInSpeechSynthesis(payload={},signal=null){
+    async #requestBuiltInSpeechSynthesis(payload={},signal=null,speechStream=null){
         const input=is.string(payload?.input)?payload.input:'';
         if(!input){
             throw new TypeError('Speech synthesis requires nonempty input.');
@@ -4703,9 +4746,15 @@ class AI {
         const speed=is.finite(payload.speed)?payload.speed:this.voiceSpeed;
         const nativeSpeech=this.#nativeSpeech(this.ttsService,'tts');
         if(nativeSpeech){
+            if(speechStream){
+                return nativeSpeech.synthesizeStream({
+                    ...payload,model,voice,input,speed
+                },{...speechStream,signal});
+            }
             let response;
             try{
                 response=await nativeSpeech.synthesize({
+                    ...payload,
                     model,
                     voice,
                     input,
@@ -6871,12 +6920,24 @@ class AI {
             if(end){
                 this.audioMessageChunks='';
                 this.#markdownSpeech.reset();
+                this.#streamSpeechOptions=null;
             }
             this.#traceSpeech('streamTTS.result',{callId,result:false,reason:'muted'});
             return Promise.resolve(false);
         }
 
-        const {voice,speed,waitForPlayback=false}=options;
+        // A final flush belongs to the same utterance selection. An explicit
+        // language change drains the previous text before accepting new text.
+        let preceding=null;
+        if(this.#streamSpeechOptions&&Object.hasOwn(options,'languageCode')
+            &&options.languageCode!==this.#streamSpeechOptions.languageCode){
+            preceding=this.streamTTS('',true,this.#streamSpeechOptions);
+        }
+        const selectedOptions={...this.#streamSpeechOptions,...options};
+        this.#streamSpeechOptions={
+            voice:selectedOptions.voice,speed:selectedOptions.speed,languageCode:selectedOptions.languageCode
+        };
+        const {voice,speed,languageCode,waitForPlayback=false}=selectedOptions;
         const pauseAfterMs=Number(options.pauseAfterMs??0);
         if(!is.finite(pauseAfterMs)||pauseAfterMs<0){
             throw new RangeError('Speech pauses must be a nonnegative number of milliseconds.');
@@ -6885,6 +6946,7 @@ class AI {
         const speechText=this.#markdownSpeech.append(String(text||''),end);
         this.audioMessageChunks+=speechText;
         const outputs=this.#extractSpeechSegments(end);
+        if(end)this.#streamSpeechOptions=null;
         this.#traceSpeech('streamTTS.segments',{
             callId,segments:outputs,remainder:this.audioMessageChunks,
             segmentation:this.ttsSegmentation,speechText
@@ -6892,7 +6954,7 @@ class AI {
 
         if(!outputs.length){
             this.#traceSpeech('streamTTS.result',{callId,result:true,reason:'buffered'});
-            return Promise.resolve(true);
+            return preceding??Promise.resolve(true);
         }
 
         try{
@@ -6909,7 +6971,7 @@ class AI {
         }
 
         const generation=this.speechGeneration;
-        const jobs=[];
+        const jobs=preceding?[preceding]:[];
         const runtime=this;
 
         for(const [index,output] of outputs.entries()){
@@ -6917,6 +6979,7 @@ class AI {
                 diagnosticCallId:callId,
                 voice,
                 speed,
+                languageCode,
                 waitForPlayback,
                 pauseAfterMs:index===outputs.length-1?pauseAfterMs:0
             }));
@@ -6938,6 +7001,7 @@ class AI {
             for(const playback of this.#preparedSpeechPlaybacks) playback.stop();
             this.audioMessageChunks='';
             this.#markdownSpeech.reset();
+            this.#streamSpeechOptions=null;
             return;
         }
         this.finishTTS();
@@ -7111,6 +7175,7 @@ class AI {
             text,
             voice:options.voice,
             speed:options.speed,
+            languageCode:options.languageCode,
             pauseAfterMs:options.pauseAfterMs??0,
             resolvePlayback:null
         };
@@ -7206,6 +7271,7 @@ class AI {
         const payload={
             model:selection?.modelId||this.modelTTS,
             input:job.text,
+            ...(job.languageCode!==undefined?{languageCode:job.languageCode}:{}),
             ...(job.voice!==undefined||voice?{voice}:{}),
             ...(!native?{responseFormat:selection
                 ?this.#providerSpeechResponseFormat()
@@ -7570,6 +7636,34 @@ class AI {
 
     async prepareTTSPlayback(payload={},signal=null,preparation={}){
         const model=this.#providerSpeechModel();
+        if(model?.speech?.streaming===true){
+            this.#assertServiceConfigured(this.ttsService,'tts');
+            if(signal?.aborted)throw normalizeAIRequestAbort(signal.reason);
+            const runtime=this;
+            const selection=this.#providerRuntime.selection('tts');
+            return prepareNativeSpeechPlayback({
+                request:{
+                    ...payload,
+                    model:payload.model??selection.modelId,
+                    voice:payload.voice??this.#providerSpeechVoice(),
+                    speed:payload.speed??this.voiceSpeed
+                },
+                signal,
+                getAudioContext:function getOwnedSpeechOutput(){
+                    return runtime.#getSpeechAudioContext();
+                },
+                speech:{
+                    synthesizeStream:function requestNativeSpeechStream(request,options){
+                        return runtime.#providerRuntime.request('tts',{
+                            operation:'synthesize',payload:request,localOnly:false,signal:options.signal
+                        },{
+                            ...preparation,
+                            speechStream:{onAudio:options.onAudio,onProgress:options.onProgress,onRequest:options.onRequest}
+                        });
+                    }
+                }
+            });
+        }
         if(model?.speech?.playback!=='native'){
             return this.fetchTTS(payload,signal,preparation);
         }
@@ -7618,6 +7712,7 @@ class AI {
                 'input',
                 'textFormat',
                 'responseFormat',
+                'languageCode',
                 'speed'
             ]);
             for(const key of Reflect.ownKeys(descriptors)){
@@ -7625,7 +7720,7 @@ class AI {
                     ||!acceptedKeys.has(key)
                     ||!Object.hasOwn(descriptors[key],'value')){
                     const error=new TypeError(
-                        'AI.fetchTTS accepts only model, voice, input, textFormat, responseFormat, and speed data properties.'
+                        'AI.fetchTTS accepts only model, voice, input, textFormat, responseFormat, languageCode, and speed data properties.'
                     );
                     error.code='ARCANE_AI_TTS_REQUEST_INVALID';
                     throw error;
@@ -7732,15 +7827,19 @@ class AI {
                 throw error;
             }
 
+            const speechRequest={
+                model,voice,input,responseFormat,speed,
+                ...(descriptors.languageCode?{languageCode:descriptors.languageCode.value}:{})
+            };
             if(selection){
                 this.#traceSpeech('fetchTTS.dispatch',{
-                    callId,selection,payload:{model,voice,input,responseFormat,speed}
+                    callId,selection,payload:speechRequest
                 });
                 const response=await this.#providerRuntime.request(
                     'tts',
                     {
                         operation:'synthesize',
-                        payload:{model,voice,input,responseFormat,speed},
+                        payload:speechRequest,
                         localOnly:false,
                         signal
                     },
@@ -7755,10 +7854,10 @@ class AI {
             }
 
             this.#traceSpeech('fetchTTS.dispatch',{
-                callId,service:this.ttsService,payload:{model,voice,input,responseFormat,speed}
+                callId,service:this.ttsService,payload:speechRequest
             });
             const audio=await this.#requestBuiltInSpeechSynthesis(
-                {model,voice,input,responseFormat,speed},
+                speechRequest,
                 signal
             );
             this.#traceSpeech('fetchTTS.result',{callId,audio});
@@ -7859,6 +7958,7 @@ class AI {
         this.speechScheduleTime=0;
         this.audioMessageChunks='';
         this.#markdownSpeech.reset();
+        this.#streamSpeechOptions=null;
         this.#clearSpeechUnlock();
 
         for(const job of this.speechJobs){