refactor: move voice-call realtime providers into extensions

src/plugin-sdk/core.ts

@@ -66,6 +66,7 @@ export type {
   ProviderReplaySessionState,
   ProviderResolveDynamicModelContext,
   ProviderResolvedUsageAuth,
+  RealtimeTranscriptionProviderPlugin,
   ProviderSanitizeReplayHistoryContext,
   ProviderToolSchemaDiagnostic,
   ProviderResolveUsageAuthContext,

src/plugin-sdk/index.ts

@@ -51,6 +51,7 @@ export type {
   ProviderAuthContext,
   ProviderAuthResult,
   ProviderRuntimeModel,
+  RealtimeTranscriptionProviderPlugin,
   SpeechProviderPlugin,
 } from "../plugins/types.js";
 export type {

src/plugin-sdk/plugin-entry.ts

@@ -46,6 +46,7 @@ import type {
   ProviderReplayPolicyContext,
   ProviderReplaySessionEntry,
   ProviderReplaySessionState,
+  RealtimeTranscriptionProviderPlugin,
   ProviderResolvedUsageAuth,
   ProviderResolveDynamicModelContext,
   ProviderSanitizeReplayHistoryContext,
@@ -102,6 +103,7 @@ export type {
   ProviderResolveDynamicModelContext,
   ProviderNormalizeResolvedModelContext,
   ProviderRuntimeModel,
+  RealtimeTranscriptionProviderPlugin,
   SpeechProviderPlugin,
   ProviderThinkingPolicyContext,
   ProviderValidateReplayTurnsContext,

src/plugin-sdk/realtime-transcription.ts

@@ -0,0 +1,16 @@
+export type { RealtimeTranscriptionProviderPlugin } from "../plugins/types.js";
+export type {
+  RealtimeTranscriptionProviderConfig,
+  RealtimeTranscriptionProviderConfiguredContext,
+  RealtimeTranscriptionProviderId,
+  RealtimeTranscriptionProviderResolveConfigContext,
+  RealtimeTranscriptionSession,
+  RealtimeTranscriptionSessionCallbacks,
+  RealtimeTranscriptionSessionCreateRequest,
+} from "../realtime-transcription/provider-types.js";
+export {
+  canonicalizeRealtimeTranscriptionProviderId,
+  getRealtimeTranscriptionProvider,
+  listRealtimeTranscriptionProviders,
+  normalizeRealtimeTranscriptionProviderId,
+} from "../realtime-transcription/provider-registry.js";

src/plugin-sdk/realtime-voice.ts

@@ -0,0 +1,20 @@
+export type { RealtimeVoiceProviderPlugin } from "../plugins/types.js";
+export type {
+  RealtimeVoiceBridge,
+  RealtimeVoiceBridgeCallbacks,
+  RealtimeVoiceBridgeCreateRequest,
+  RealtimeVoiceCloseReason,
+  RealtimeVoiceProviderConfig,
+  RealtimeVoiceProviderConfiguredContext,
+  RealtimeVoiceProviderId,
+  RealtimeVoiceProviderResolveConfigContext,
+  RealtimeVoiceRole,
+  RealtimeVoiceTool,
+  RealtimeVoiceToolCallEvent,
+} from "../realtime-voice/provider-types.js";
+export {
+  canonicalizeRealtimeVoiceProviderId,
+  getRealtimeVoiceProvider,
+  listRealtimeVoiceProviders,
+  normalizeRealtimeVoiceProviderId,
+} from "../realtime-voice/provider-registry.js";

src/plugin-sdk/speech.ts

@@ -1,7 +1,12 @@
+import { rmSync } from "node:fs";
+import type { OpenClawConfig } from "../config/config.js";
+import type { ResolvedTtsConfig } from "../tts/tts.js";
+
 // Public speech helpers for bundled or third-party plugins.
 //
-// Keep this surface neutral. Provider plugins should not need to know about the
-// bundled `speech-core` plugin id just to consume shared speech types/helpers.
+// Keep this surface neutral and import-light. Provider builders commonly import
+// this module just to get types and a few validation helpers, so avoid pulling
+// in the heavy TTS runtime graph at module load time.
 
 export type { SpeechProviderPlugin } from "../plugins/types.js";
 export type {
@@ -22,14 +27,6 @@ export type {
   TtsDirectiveParseResult,
 } from "../tts/provider-types.js";
 
-export {
-  scheduleCleanup,
-  summarizeText,
-  normalizeApplyTextNormalization,
-  normalizeLanguageCode,
-  normalizeSeed,
-  requireInRange,
-} from "../tts/tts-core.js";
 export { parseTtsDirectives } from "../tts/directives.js";
 export {
   canonicalizeSpeechProviderId,
@@ -44,3 +41,71 @@ export {
   trimToUndefined,
   truncateErrorDetail,
 } from "../tts/provider-error-utils.js";
+
+const TEMP_FILE_CLEANUP_DELAY_MS = 5 * 60 * 1000; // 5 minutes
+
+export function requireInRange(value: number, min: number, max: number, label: string): void {
+  if (!Number.isFinite(value) || value < min || value > max) {
+    throw new Error(`${label} must be between ${min} and ${max}`);
+  }
+}
+
+export function normalizeLanguageCode(code?: string): string | undefined {
+  const trimmed = code?.trim();
+  if (!trimmed) {
+    return undefined;
+  }
+  const normalized = trimmed.toLowerCase();
+  if (!/^[a-z]{2}$/.test(normalized)) {
+    throw new Error("languageCode must be a 2-letter ISO 639-1 code (e.g. en, de, fr)");
+  }
+  return normalized;
+}
+
+export function normalizeApplyTextNormalization(mode?: string): "auto" | "on" | "off" | undefined {
+  const trimmed = mode?.trim();
+  if (!trimmed) {
+    return undefined;
+  }
+  const normalized = trimmed.toLowerCase();
+  if (normalized === "auto" || normalized === "on" || normalized === "off") {
+    return normalized;
+  }
+  throw new Error("applyTextNormalization must be one of: auto, on, off");
+}
+
+export function normalizeSeed(seed?: number): number | undefined {
+  if (seed == null) {
+    return undefined;
+  }
+  const next = Math.floor(seed);
+  if (!Number.isFinite(next) || next < 0 || next > 4_294_967_295) {
+    throw new Error("seed must be between 0 and 4294967295");
+  }
+  return next;
+}
+
+export function scheduleCleanup(
+  tempDir: string,
+  delayMs: number = TEMP_FILE_CLEANUP_DELAY_MS,
+): void {
+  const timer = setTimeout(() => {
+    try {
+      rmSync(tempDir, { recursive: true, force: true });
+    } catch {
+      // ignore cleanup errors
+    }
+  }, delayMs);
+  timer.unref();
+}
+
+export async function summarizeText(params: {
+  text: string;
+  targetLength: number;
+  cfg: OpenClawConfig;
+  config: ResolvedTtsConfig;
+  timeoutMs: number;
+}) {
+  const { summarizeText: summarizeTextRuntime } = await import("../tts/tts-core.js");
+  return summarizeTextRuntime(params);
+}