@deepseek-ai/dsh-experimental-api-speech-to-text 0.1.7-alpha.1

package/lib/typert.remote-client.js

@@ -0,0 +1,311 @@
+/* Generated by @deepseek-ai/dsh-typert-generator from the Host FaceModel — do not edit. */
+import { z } from 'zod'
+
+let _deepseek_ai_dsh_experimental_api_speech_to_text_speech_cancelPreparation_parameter_0$schema$value
+const _deepseek_ai_dsh_experimental_api_speech_to_text_speech_cancelPreparation_parameter_0$schema = () => (_deepseek_ai_dsh_experimental_api_speech_to_text_speech_cancelPreparation_parameter_0$schema$value ??= z.intersection(z.string(), z.unknown()))
+let _deepseek_ai_dsh_experimental_api_speech_to_text_speech_cancelPreparation_result$schema$value
+const _deepseek_ai_dsh_experimental_api_speech_to_text_speech_cancelPreparation_result$schema = () => (_deepseek_ai_dsh_experimental_api_speech_to_text_speech_cancelPreparation_result$schema$value ??= z.void())
+let _deepseek_ai_dsh_experimental_api_speech_to_text_speech_catalog_result$schema$value
+const _deepseek_ai_dsh_experimental_api_speech_to_text_speech_catalog_result$schema = () => (_deepseek_ai_dsh_experimental_api_speech_to_text_speech_catalog_result$schema$value ??= z.object({
+  'maxAudioBytes': z.number().readonly(),
+  'maxDurationSeconds': z.number().readonly(),
+  'providers': z.array(z.object({
+  'preparation': z.union([z.intersection(z.object({
+  'phase': z.union([z.literal("cancelled"), z.literal("ready"), z.literal("unprepared"), z.literal("standby")]).readonly(),
+}), z.object({
+  'step': z.union([z.literal("check"), z.literal("model"), z.literal("vad"), z.literal("verify"), z.literal("load")]).readonly().optional(),
+  'steps': z.array(z.object({
+  'kind': z.union([z.literal("check"), z.literal("model"), z.literal("vad"), z.literal("verify"), z.literal("load")]).readonly(),
+  'status': z.union([z.literal("cancelled"), z.literal("failed"), z.literal("running"), z.literal("pending"), z.literal("complete")]).readonly(),
+  'startedAt': z.number().readonly().optional(),
+})).readonly().optional(),
+})), z.intersection(z.object({
+  'phase': z.literal("downloading").readonly(),
+  'resource': z.string().readonly(),
+  'completedBytes': z.number().readonly(),
+  'totalBytes': z.number().readonly().optional(),
+}), z.object({
+  'step': z.union([z.literal("check"), z.literal("model"), z.literal("vad"), z.literal("verify"), z.literal("load")]).readonly().optional(),
+  'steps': z.array(z.object({
+  'kind': z.union([z.literal("check"), z.literal("model"), z.literal("vad"), z.literal("verify"), z.literal("load")]).readonly(),
+  'status': z.union([z.literal("cancelled"), z.literal("failed"), z.literal("running"), z.literal("pending"), z.literal("complete")]).readonly(),
+  'startedAt': z.number().readonly().optional(),
+})).readonly().optional(),
+})), z.intersection(z.object({
+  'phase': z.union([z.literal("checking"), z.literal("loading"), z.literal("waking"), z.literal("cancelling")]).readonly(),
+  'startedAt': z.number().readonly(),
+}), z.object({
+  'step': z.union([z.literal("check"), z.literal("model"), z.literal("vad"), z.literal("verify"), z.literal("load")]).readonly().optional(),
+  'steps': z.array(z.object({
+  'kind': z.union([z.literal("check"), z.literal("model"), z.literal("vad"), z.literal("verify"), z.literal("load")]).readonly(),
+  'status': z.union([z.literal("cancelled"), z.literal("failed"), z.literal("running"), z.literal("pending"), z.literal("complete")]).readonly(),
+  'startedAt': z.number().readonly().optional(),
+})).readonly().optional(),
+})), z.intersection(z.object({
+  'phase': z.literal("failed").readonly(),
+  'message': z.string().readonly(),
+  'download': z.object({
+  'resource': z.string().readonly(),
+  'source': z.string().readonly(),
+  'reason': z.union([z.literal("network"), z.literal("storage"), z.literal("unknown"), z.literal("dns"), z.literal("timeout"), z.literal("certificate"), z.literal("http"), z.literal("integrity")]).readonly(),
+  'code': z.string().readonly().optional(),
+  'status': z.number().readonly().optional(),
+}).readonly().optional(),
+}), z.object({
+  'step': z.union([z.literal("check"), z.literal("model"), z.literal("vad"), z.literal("verify"), z.literal("load")]).readonly().optional(),
+  'steps': z.array(z.object({
+  'kind': z.union([z.literal("check"), z.literal("model"), z.literal("vad"), z.literal("verify"), z.literal("load")]).readonly(),
+  'status': z.union([z.literal("cancelled"), z.literal("failed"), z.literal("running"), z.literal("pending"), z.literal("complete")]).readonly(),
+  'startedAt': z.number().readonly().optional(),
+})).readonly().optional(),
+}))]).readonly(),
+  'id': z.intersection(z.string(), z.unknown()).readonly(),
+  'name': z.string().readonly(),
+  'location': z.union([z.literal("host-local"), z.literal("cloud")]).readonly(),
+  'languages': z.array(z.string()).readonly(),
+  'setupEstimate': z.object({
+  'recommendedDiskBytes': z.number().readonly(),
+  'expectedMemoryBytes': z.number().readonly(),
+  'minimumMinutes': z.number().readonly(),
+  'maximumMinutes': z.number().readonly(),
+}).readonly().optional(),
+})).readonly(),
+  'selection': z.object({
+  'providerId': z.intersection(z.string(), z.unknown()).readonly(),
+  'language': z.string().readonly(),
+}).readonly(),
+}))
+let _deepseek_ai_dsh_experimental_api_speech_to_text_speech_configure_parameter_0$schema$value
+const _deepseek_ai_dsh_experimental_api_speech_to_text_speech_configure_parameter_0$schema = () => (_deepseek_ai_dsh_experimental_api_speech_to_text_speech_configure_parameter_0$schema$value ??= z.object({
+  'providerId': z.intersection(z.string(), z.unknown()).readonly().optional(),
+  'language': z.string().readonly().optional(),
+}))
+let _deepseek_ai_dsh_experimental_api_speech_to_text_speech_configure_result$schema$value
+const _deepseek_ai_dsh_experimental_api_speech_to_text_speech_configure_result$schema = () => (_deepseek_ai_dsh_experimental_api_speech_to_text_speech_configure_result$schema$value ??= z.void())
+let _deepseek_ai_dsh_experimental_api_speech_to_text_speech_follow_result$schema$value
+const _deepseek_ai_dsh_experimental_api_speech_to_text_speech_follow_result$schema = () => (_deepseek_ai_dsh_experimental_api_speech_to_text_speech_follow_result$schema$value ??= z.object({
+  'maxAudioBytes': z.number().readonly(),
+  'maxDurationSeconds': z.number().readonly(),
+  'providers': z.array(z.object({
+  'preparation': z.union([z.intersection(z.object({
+  'phase': z.union([z.literal("cancelled"), z.literal("ready"), z.literal("unprepared"), z.literal("standby")]).readonly(),
+}), z.object({
+  'step': z.union([z.literal("check"), z.literal("model"), z.literal("vad"), z.literal("verify"), z.literal("load")]).readonly().optional(),
+  'steps': z.array(z.object({
+  'kind': z.union([z.literal("check"), z.literal("model"), z.literal("vad"), z.literal("verify"), z.literal("load")]).readonly(),
+  'status': z.union([z.literal("cancelled"), z.literal("failed"), z.literal("running"), z.literal("pending"), z.literal("complete")]).readonly(),
+  'startedAt': z.number().readonly().optional(),
+})).readonly().optional(),
+})), z.intersection(z.object({
+  'phase': z.literal("downloading").readonly(),
+  'resource': z.string().readonly(),
+  'completedBytes': z.number().readonly(),
+  'totalBytes': z.number().readonly().optional(),
+}), z.object({
+  'step': z.union([z.literal("check"), z.literal("model"), z.literal("vad"), z.literal("verify"), z.literal("load")]).readonly().optional(),
+  'steps': z.array(z.object({
+  'kind': z.union([z.literal("check"), z.literal("model"), z.literal("vad"), z.literal("verify"), z.literal("load")]).readonly(),
+  'status': z.union([z.literal("cancelled"), z.literal("failed"), z.literal("running"), z.literal("pending"), z.literal("complete")]).readonly(),
+  'startedAt': z.number().readonly().optional(),
+})).readonly().optional(),
+})), z.intersection(z.object({
+  'phase': z.union([z.literal("checking"), z.literal("loading"), z.literal("waking"), z.literal("cancelling")]).readonly(),
+  'startedAt': z.number().readonly(),
+}), z.object({
+  'step': z.union([z.literal("check"), z.literal("model"), z.literal("vad"), z.literal("verify"), z.literal("load")]).readonly().optional(),
+  'steps': z.array(z.object({
+  'kind': z.union([z.literal("check"), z.literal("model"), z.literal("vad"), z.literal("verify"), z.literal("load")]).readonly(),
+  'status': z.union([z.literal("cancelled"), z.literal("failed"), z.literal("running"), z.literal("pending"), z.literal("complete")]).readonly(),
+  'startedAt': z.number().readonly().optional(),
+})).readonly().optional(),
+})), z.intersection(z.object({
+  'phase': z.literal("failed").readonly(),
+  'message': z.string().readonly(),
+  'download': z.object({
+  'resource': z.string().readonly(),
+  'source': z.string().readonly(),
+  'reason': z.union([z.literal("network"), z.literal("storage"), z.literal("unknown"), z.literal("dns"), z.literal("timeout"), z.literal("certificate"), z.literal("http"), z.literal("integrity")]).readonly(),
+  'code': z.string().readonly().optional(),
+  'status': z.number().readonly().optional(),
+}).readonly().optional(),
+}), z.object({
+  'step': z.union([z.literal("check"), z.literal("model"), z.literal("vad"), z.literal("verify"), z.literal("load")]).readonly().optional(),
+  'steps': z.array(z.object({
+  'kind': z.union([z.literal("check"), z.literal("model"), z.literal("vad"), z.literal("verify"), z.literal("load")]).readonly(),
+  'status': z.union([z.literal("cancelled"), z.literal("failed"), z.literal("running"), z.literal("pending"), z.literal("complete")]).readonly(),
+  'startedAt': z.number().readonly().optional(),
+})).readonly().optional(),
+}))]).readonly(),
+  'id': z.intersection(z.string(), z.unknown()).readonly(),
+  'name': z.string().readonly(),
+  'location': z.union([z.literal("host-local"), z.literal("cloud")]).readonly(),
+  'languages': z.array(z.string()).readonly(),
+  'setupEstimate': z.object({
+  'recommendedDiskBytes': z.number().readonly(),
+  'expectedMemoryBytes': z.number().readonly(),
+  'minimumMinutes': z.number().readonly(),
+  'maximumMinutes': z.number().readonly(),
+}).readonly().optional(),
+})).readonly(),
+  'selection': z.object({
+  'providerId': z.intersection(z.string(), z.unknown()).readonly(),
+  'language': z.string().readonly(),
+}).readonly(),
+}))
+let _deepseek_ai_dsh_experimental_api_speech_to_text_speech_prepare_parameter_0$schema$value
+const _deepseek_ai_dsh_experimental_api_speech_to_text_speech_prepare_parameter_0$schema = () => (_deepseek_ai_dsh_experimental_api_speech_to_text_speech_prepare_parameter_0$schema$value ??= z.intersection(z.string(), z.unknown()))
+let _deepseek_ai_dsh_experimental_api_speech_to_text_speech_prepare_result$schema$value
+const _deepseek_ai_dsh_experimental_api_speech_to_text_speech_prepare_result$schema = () => (_deepseek_ai_dsh_experimental_api_speech_to_text_speech_prepare_result$schema$value ??= z.void())
+let _deepseek_ai_dsh_experimental_api_speech_to_text_speech_transcribe_parameter_0$schema$value
+const _deepseek_ai_dsh_experimental_api_speech_to_text_speech_transcribe_parameter_0$schema = () => (_deepseek_ai_dsh_experimental_api_speech_to_text_speech_transcribe_parameter_0$schema$value ??= z.object({
+  'audioBase64': z.string().readonly(),
+  'providerId': z.intersection(z.string(), z.unknown()).readonly().optional(),
+  'language': z.string().readonly().optional(),
+}))
+let _deepseek_ai_dsh_experimental_api_speech_to_text_speech_transcribe_result$schema$value
+const _deepseek_ai_dsh_experimental_api_speech_to_text_speech_transcribe_result$schema = () => (_deepseek_ai_dsh_experimental_api_speech_to_text_speech_transcribe_result$schema$value ??= z.object({
+  'text': z.string().readonly(),
+  'audioSeconds': z.number().readonly(),
+  'inferenceSeconds': z.number().readonly(),
+}))
+
+export const TYPERT_REMOTE = {
+  package: '@deepseek-ai/dsh-experimental-api-speech-to-text',
+  descriptors: [
+    {
+      id: '@deepseek-ai/dsh-experimental-api-speech-to-text#speech/cancelPreparation',
+      service: 'speechController',
+      namespace: 'speech',
+      method: 'cancelPreparation',
+      invocation: { kind: 'direct' },
+      parameters: [
+        {
+          name: 'providerId',
+          wire: 'providerId',
+          source: 'json',
+          codec: {
+            mode: 'strict',
+            typeSymbol: '@deepseek-ai/dsh-experimental-speech-to-text/types#SpeechProviderId',
+            create: _deepseek_ai_dsh_experimental_api_speech_to_text_speech_cancelPreparation_parameter_0$schema,
+          },
+        },
+      ],
+      result: {
+        mode: 'strict',
+        typeSymbol: '@deepseek-ai/dsh-experimental-api-speech-to-text#speech/cancelPreparation:result',
+        create: _deepseek_ai_dsh_experimental_api_speech_to_text_speech_cancelPreparation_result$schema,
+      },
+      sourceLocation: {"file":"packages/experimental/api-speech-to-text/src/index.ts","line":79,"column":3},
+    },
+    {
+      id: '@deepseek-ai/dsh-experimental-api-speech-to-text#speech/catalog',
+      service: 'speechController',
+      namespace: 'speech',
+      method: 'catalog',
+      invocation: { kind: 'direct' },
+      parameters: [
+      ],
+      result: {
+        mode: 'strict',
+        typeSymbol: '@deepseek-ai/dsh-experimental-api-speech-to-text/types#SpeechCatalog',
+        create: _deepseek_ai_dsh_experimental_api_speech_to_text_speech_catalog_result$schema,
+      },
+      sourceLocation: {"file":"packages/experimental/api-speech-to-text/src/index.ts","line":44,"column":3},
+    },
+    {
+      id: '@deepseek-ai/dsh-experimental-api-speech-to-text#speech/configure',
+      service: 'speechController',
+      namespace: 'speech',
+      method: 'configure',
+      invocation: { kind: 'direct' },
+      parameters: [
+        {
+          name: 'patch',
+          wire: 'patch',
+          source: 'json',
+          codec: {
+            mode: 'strict',
+            typeSymbol: '@deepseek-ai/dsh-experimental-speech-to-text/types#SpeechSelectionPatch',
+            create: _deepseek_ai_dsh_experimental_api_speech_to_text_speech_configure_parameter_0$schema,
+          },
+        },
+      ],
+      result: {
+        mode: 'strict',
+        typeSymbol: '@deepseek-ai/dsh-experimental-api-speech-to-text#speech/configure:result',
+        create: _deepseek_ai_dsh_experimental_api_speech_to_text_speech_configure_result$schema,
+      },
+      sourceLocation: {"file":"packages/experimental/api-speech-to-text/src/index.ts","line":64,"column":3},
+    },
+    {
+      id: '@deepseek-ai/dsh-experimental-api-speech-to-text#speech/follow',
+      service: 'speechController',
+      namespace: 'speech',
+      method: 'follow',
+      mode: 'stream',
+      invocation: { kind: 'direct' },
+      parameters: [
+      ],
+      cancellation: { parameter: 'signal' },
+      result: {
+        mode: 'strict',
+        typeSymbol: '@deepseek-ai/dsh-experimental-api-speech-to-text/types#SpeechCatalog',
+        create: _deepseek_ai_dsh_experimental_api_speech_to_text_speech_follow_result$schema,
+      },
+      sourceLocation: {"file":"packages/experimental/api-speech-to-text/src/index.ts","line":54,"column":10},
+    },
+    {
+      id: '@deepseek-ai/dsh-experimental-api-speech-to-text#speech/prepare',
+      service: 'speechController',
+      namespace: 'speech',
+      method: 'prepare',
+      invocation: { kind: 'direct' },
+      parameters: [
+        {
+          name: 'providerId',
+          wire: 'providerId',
+          source: 'json',
+          codec: {
+            mode: 'strict',
+            typeSymbol: '@deepseek-ai/dsh-experimental-speech-to-text/types#SpeechProviderId',
+            create: _deepseek_ai_dsh_experimental_api_speech_to_text_speech_prepare_parameter_0$schema,
+          },
+        },
+      ],
+      result: {
+        mode: 'strict',
+        typeSymbol: '@deepseek-ai/dsh-experimental-api-speech-to-text#speech/prepare:result',
+        create: _deepseek_ai_dsh_experimental_api_speech_to_text_speech_prepare_result$schema,
+      },
+      sourceLocation: {"file":"packages/experimental/api-speech-to-text/src/index.ts","line":71,"column":3},
+    },
+    {
+      id: '@deepseek-ai/dsh-experimental-api-speech-to-text#speech/transcribe',
+      service: 'speechController',
+      namespace: 'speech',
+      method: 'transcribe',
+      invocation: { kind: 'direct' },
+      parameters: [
+        {
+          name: 'request',
+          wire: 'request',
+          source: 'json',
+          codec: {
+            mode: 'strict',
+            typeSymbol: '@deepseek-ai/dsh-experimental-api-speech-to-text/types#TranscriptionRequest',
+            create: _deepseek_ai_dsh_experimental_api_speech_to_text_speech_transcribe_parameter_0$schema,
+          },
+        },
+      ],
+      cancellation: { parameter: 'signal' },
+      result: {
+        mode: 'strict',
+        typeSymbol: '@deepseek-ai/dsh-experimental-speech-to-text/types#Transcript',
+        create: _deepseek_ai_dsh_experimental_api_speech_to_text_speech_transcribe_result$schema,
+      },
+      sourceLocation: {"file":"packages/experimental/api-speech-to-text/src/index.ts","line":88,"column":9},
+    },
+  ],
+}
+
+export default TYPERT_REMOTE

package/lib/types/index.d.ts

@@ -0,0 +1,63 @@
+/** Authenticated, cancellation-aware Client access to the speech capability. */
+import { Context } from '@deepseek-ai/cordis';
+import z from '@deepseek-ai/schemastery';
+import { TypertRemoteService } from '@deepseek-ai/dsh-typert-protocol';
+import type { SpeechProviderId, SpeechSelectionPatch, Transcript } from '@deepseek-ai/dsh-experimental-speech-to-text/types';
+import type { SpeechCatalog, TranscriptionRequest } from './types.ts';
+export type * from './types.ts';
+declare module '@deepseek-ai/cordis' {
+    interface Context {
+        /** Experimental speech Remote controller. */
+        speechController: SpeechController;
+    }
+}
+/** Limits applied before decoding or calling a provider. */
+export interface Config {
+    /** Maximum decoded WAV bytes per request. */
+    maxAudioBytes: number;
+    /** Maximum PCM recording duration in seconds. */
+    maxDurationSeconds: number;
+}
+/** Speech calls never activate or submit to an Agent. */
+export default class SpeechController extends TypertRemoteService {
+    private readonly config;
+    static inject: string[];
+    static Config: z<Config>;
+    constructor(ctx: Context, config: Config);
+    /**
+     * Read provider choices without preparing a recognizer.
+     * @returns available providers, resolved default, and recording limits.
+     */
+    catalog(): SpeechCatalog;
+    /**
+     * Follow provider readiness independently of Session and preparation lifetimes.
+     * @param signal - Client observation lifetime.
+     * @returns initial and subsequent complete readiness snapshots.
+     */
+    follow(signal: AbortSignal): AsyncIterable<SpeechCatalog>;
+    /**
+     * Persist the user's recognition preferences.
+     * @param patch - changed preference fields.
+     * @returns after preferences are saved.
+     */
+    configure(patch: SpeechSelectionPatch): Promise<void>;
+    /**
+     * Start or join one Host-owned preparation task.
+     * @param providerId - selected recognizer.
+     */
+    prepare(providerId: SpeechProviderId): void;
+    /**
+     * Explicitly cancel resource preparation.
+     * @param providerId - selected recognizer.
+     * @returns after the preparation task settles.
+     */
+    cancelPreparation(providerId: SpeechProviderId): Promise<void>;
+    /**
+     * Validate and transcribe one recording through the explicit provider selection.
+     * @param request - canonical WAV encoded as base64, provider id and language hint.
+     * @param signal - Client cancellation or Remote contribution disposal.
+     * @returns final transcript without adding a Session event.
+     */
+    transcribe(request: TranscriptionRequest, signal: AbortSignal): Promise<Transcript>;
+}
+//# sourceMappingURL=index.d.ts.map

package/lib/types/index.js

@@ -0,0 +1,142 @@
+var __runInitializers = (this && this.__runInitializers) || function (thisArg, initializers, value) {
+    var useValue = arguments.length > 2;
+    for (var i = 0; i < initializers.length; i++) {
+        value = useValue ? initializers[i].call(thisArg, value) : initializers[i].call(thisArg);
+    }
+    return useValue ? value : void 0;
+};
+var __esDecorate = (this && this.__esDecorate) || function (ctor, descriptorIn, decorators, contextIn, initializers, extraInitializers) {
+    function accept(f) { if (f !== void 0 && typeof f !== "function") throw new TypeError("Function expected"); return f; }
+    var kind = contextIn.kind, key = kind === "getter" ? "get" : kind === "setter" ? "set" : "value";
+    var target = !descriptorIn && ctor ? contextIn["static"] ? ctor : ctor.prototype : null;
+    var descriptor = descriptorIn || (target ? Object.getOwnPropertyDescriptor(target, contextIn.name) : {});
+    var _, done = false;
+    for (var i = decorators.length - 1; i >= 0; i--) {
+        var context = {};
+        for (var p in contextIn) context[p] = p === "access" ? {} : contextIn[p];
+        for (var p in contextIn.access) context.access[p] = contextIn.access[p];
+        context.addInitializer = function (f) { if (done) throw new TypeError("Cannot add initializers after decoration has completed"); extraInitializers.push(accept(f || null)); };
+        var result = (0, decorators[i])(kind === "accessor" ? { get: descriptor.get, set: descriptor.set } : descriptor[key], context);
+        if (kind === "accessor") {
+            if (result === void 0) continue;
+            if (result === null || typeof result !== "object") throw new TypeError("Object expected");
+            if (_ = accept(result.get)) descriptor.get = _;
+            if (_ = accept(result.set)) descriptor.set = _;
+            if (_ = accept(result.init)) initializers.unshift(_);
+        }
+        else if (_ = accept(result)) {
+            if (kind === "field") initializers.unshift(_);
+            else descriptor[key] = _;
+        }
+    }
+    if (target) Object.defineProperty(target, contextIn.name, descriptor);
+    done = true;
+};
+import z from '@deepseek-ai/schemastery';
+import { Remote, RemoteError, TypertRemoteService } from '@deepseek-ai/dsh-typert-protocol';
+import { validateWave } from '@deepseek-ai/dsh-experimental-speech-to-text/wave';
+let SpeechController = (() => {
+    let _classSuper = TypertRemoteService;
+    let _instanceExtraInitializers = [];
+    let _catalog_decorators;
+    let _follow_decorators;
+    let _configure_decorators;
+    let _prepare_decorators;
+    let _cancelPreparation_decorators;
+    let _transcribe_decorators;
+    return class SpeechController extends _classSuper {
+        static {
+            const _metadata = typeof Symbol === "function" && Symbol.metadata ? Object.create(_classSuper[Symbol.metadata] ?? null) : void 0;
+            _catalog_decorators = [Remote];
+            _follow_decorators = [Remote({ mode: 'stream' })];
+            _configure_decorators = [Remote];
+            _prepare_decorators = [Remote];
+            _cancelPreparation_decorators = [Remote];
+            _transcribe_decorators = [Remote];
+            __esDecorate(this, null, _catalog_decorators, { kind: "method", name: "catalog", static: false, private: false, access: { has: obj => "catalog" in obj, get: obj => obj.catalog }, metadata: _metadata }, null, _instanceExtraInitializers);
+            __esDecorate(this, null, _follow_decorators, { kind: "method", name: "follow", static: false, private: false, access: { has: obj => "follow" in obj, get: obj => obj.follow }, metadata: _metadata }, null, _instanceExtraInitializers);
+            __esDecorate(this, null, _configure_decorators, { kind: "method", name: "configure", static: false, private: false, access: { has: obj => "configure" in obj, get: obj => obj.configure }, metadata: _metadata }, null, _instanceExtraInitializers);
+            __esDecorate(this, null, _prepare_decorators, { kind: "method", name: "prepare", static: false, private: false, access: { has: obj => "prepare" in obj, get: obj => obj.prepare }, metadata: _metadata }, null, _instanceExtraInitializers);
+            __esDecorate(this, null, _cancelPreparation_decorators, { kind: "method", name: "cancelPreparation", static: false, private: false, access: { has: obj => "cancelPreparation" in obj, get: obj => obj.cancelPreparation }, metadata: _metadata }, null, _instanceExtraInitializers);
+            __esDecorate(this, null, _transcribe_decorators, { kind: "method", name: "transcribe", static: false, private: false, access: { has: obj => "transcribe" in obj, get: obj => obj.transcribe }, metadata: _metadata }, null, _instanceExtraInitializers);
+            if (_metadata) Object.defineProperty(this, Symbol.metadata, { enumerable: true, configurable: true, writable: true, value: _metadata });
+        }
+        config = __runInitializers(this, _instanceExtraInitializers);
+        static inject = ['speechToText', 'typert'];
+        static Config = z.object({
+            maxAudioBytes: z.natural().min(46).default(4 * 1024 * 1024),
+            maxDurationSeconds: z.number().min(1).default(120),
+        });
+        constructor(ctx, config) {
+            super(ctx, 'speechController', { namespace: 'speech' });
+            this.config = config;
+        }
+        /**
+         * Read provider choices without preparing a recognizer.
+         * @returns available providers, resolved default, and recording limits.
+         */
+        catalog() {
+            return { ...this.ctx.speechToText.snapshot(), ...this.config };
+        }
+        /**
+         * Follow provider readiness independently of Session and preparation lifetimes.
+         * @param signal - Client observation lifetime.
+         * @returns initial and subsequent complete readiness snapshots.
+         */
+        async *follow(signal) {
+            for await (const snapshot of this.ctx.speechToText.follow(signal))
+                yield { ...snapshot, ...this.config };
+        }
+        /**
+         * Persist the user's recognition preferences.
+         * @param patch - changed preference fields.
+         * @returns after preferences are saved.
+         */
+        configure(patch) { return this.ctx.speechToText.configure(patch); }
+        /**
+         * Start or join one Host-owned preparation task.
+         * @param providerId - selected recognizer.
+         */
+        prepare(providerId) { this.ctx.speechToText.prepare(providerId); }
+        /**
+         * Explicitly cancel resource preparation.
+         * @param providerId - selected recognizer.
+         * @returns after the preparation task settles.
+         */
+        cancelPreparation(providerId) { return this.ctx.speechToText.cancelPreparation(providerId); }
+        /**
+         * Validate and transcribe one recording through the explicit provider selection.
+         * @param request - canonical WAV encoded as base64, provider id and language hint.
+         * @param signal - Client cancellation or Remote contribution disposal.
+         * @returns final transcript without adding a Session event.
+         */
+        async transcribe(request, signal) {
+            signal.throwIfAborted();
+            const encoded = request.audioBase64;
+            if (encoded.length > Math.ceil(this.config.maxAudioBytes / 3) * 4) {
+                throw new RemoteError('speech/invalid-audio', 'Audio is invalid or exceeds the configured byte limit', { reason: 'encoding-or-size' });
+            }
+            const audio = Buffer.from(encoded, 'base64');
+            try {
+                if (audio.toString('base64') !== encoded)
+                    throw new Error('Audio must use canonical base64 encoding');
+                if (audio.length > this.config.maxAudioBytes)
+                    throw new Error('Audio exceeds the configured byte limit');
+                validateWave(audio, this.config.maxDurationSeconds);
+                const spec = this.ctx.speechToText.resolve({ audio,
+                    ...request.providerId === undefined ? {} : { providerId: request.providerId },
+                    ...request.language === undefined ? {} : { language: request.language },
+                });
+                return await this.ctx.speechToText.transcribe(spec, signal);
+            }
+            catch (error) {
+                signal.throwIfAborted();
+                const reason = error instanceof Error ? error.message : String(error);
+                throw new RemoteError('speech/transcription-failed', reason, { reason });
+            }
+        }
+    };
+})();
+/** Speech calls never activate or submit to an Agent. */
+export default SpeechController;
+//# sourceMappingURL=index.js.map

package/lib/types/types.d.ts

@@ -0,0 +1,26 @@
+/** JSON-safe inputs and results of the experimental speech Remote namespace. */
+import type { SpeechProviderId, SpeechSnapshot } from '@deepseek-ai/dsh-experimental-speech-to-text/types';
+declare module '@deepseek-ai/dsh-typert-protocol' {
+    interface RemoteErrorDetailsMap {
+        /** Audio encoding or intake limits prevented transcription. */
+        'speech/invalid-audio': {
+            readonly reason: string;
+        };
+        /** The selected provider rejected transcription. */
+        'speech/transcription-failed': {
+            readonly reason: string;
+        };
+    }
+}
+/** Complete recording submitted for transcription, separate from Session admission. */
+export interface TranscriptionRequest {
+    readonly audioBase64: string;
+    readonly providerId?: SpeechProviderId;
+    readonly language?: string;
+}
+/** Current provider choices and audio intake limits. */
+export interface SpeechCatalog extends SpeechSnapshot {
+    readonly maxAudioBytes: number;
+    readonly maxDurationSeconds: number;
+}
+//# sourceMappingURL=types.d.ts.map

package/lib/types/types.js

@@ -0,0 +1,2 @@
+export {};
+//# sourceMappingURL=types.js.map

package/package.json

@@ -0,0 +1,60 @@
+{
+  "name": "@deepseek-ai/dsh-experimental-api-speech-to-text",
+  "description": "Authenticated experimental speech transcription for browser clients",
+  "version": "0.1.7-alpha.1",
+  "publishConfig": {
+    "access": "public"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/deepseek-ai/deepseek-harness.git",
+    "directory": "packages/experimental/api-speech-to-text"
+  },
+  "type": "module",
+  "main": "lib/index.js",
+  "types": "lib/types/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./lib/types/index.d.ts",
+      "default": "./lib/index.js"
+    },
+    "./src/*": "./src/*",
+    "./package.json": "./package.json",
+    "./types": {
+      "types": "./lib/types/types.d.ts",
+      "default": "./lib/types/types.js"
+    },
+    "./typert": {
+      "types": "./lib/typert.host.d.ts",
+      "default": "./lib/typert.host.js"
+    },
+    "./remote": {
+      "types": "./lib/typert.remote-client.d.ts",
+      "default": "./lib/typert.remote-client.js"
+    }
+  },
+  "files": [
+    "lib/index.js",
+    "lib/types/**/*.js",
+    "lib/types/**/*.d.ts",
+    "lib/typert.host.js",
+    "lib/typert.host.d.ts",
+    "lib/typert.remote-client.js",
+    "lib/typert.remote-client.d.ts"
+  ],
+  "license": "MIT",
+  "dependencies": {
+    "zod": "^4.4.3",
+    "@deepseek-ai/schemastery": "^3.18.3"
+  },
+  "peerDependencies": {
+    "@deepseek-ai/dsh-experimental-speech-to-text": "^0.1.7-alpha.1",
+    "@deepseek-ai/cordis": "^4.0.3",
+    "@deepseek-ai/dsh-typert-protocol": "^0.1.7-alpha.1"
+  },
+  "devDependencies": {
+    "@deepseek-ai/cordis": "^4.0.3",
+    "@deepseek-ai/dsh-experimental-speech-to-text": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-typert-protocol": "^0.1.7-alpha.1"
+  }
+}