From 4a0341ed035cae117ee560def33a74e87dd036ef Mon Sep 17 00:00:00 2001
From: Ayaan Zaidi <hi@obviy.us>
Date: Fri, 20 Mar 2026 10:45:32 +0530
Subject: [PATCH] fix(review): address talk cleanup feedback

---
 .../ai/openclaw/app/voice/TalkModeManager.kt  |  7 +-
 src/gateway/server-methods/talk.ts            | 99 +++++++------------
 2 files changed, 39 insertions(+), 67 deletions(-)

diff --git a/apps/android/app/src/main/java/ai/openclaw/app/voice/TalkModeManager.kt b/apps/android/app/src/main/java/ai/openclaw/app/voice/TalkModeManager.kt
index 4ba2c2ef043..be62498e24e 100644
--- a/apps/android/app/src/main/java/ai/openclaw/app/voice/TalkModeManager.kt
+++ b/apps/android/app/src/main/java/ai/openclaw/app/voice/TalkModeManager.kt
@@ -756,12 +756,9 @@ class TalkModeManager(
       }
     val suffix = resolveGatewayAudioSuffix(speech)
     val tempFile =
-      withContext(Dispatchers.IO) {
-        File.createTempFile("tts_", suffix, context.cacheDir).apply {
-          writeBytes(audioBytes)
-        }
-      }
+      withContext(Dispatchers.IO) { File.createTempFile("tts_", suffix, context.cacheDir) }
     try {
+      withContext(Dispatchers.IO) { tempFile.writeBytes(audioBytes) }
       val player = MediaPlayer()
       this.player = player
       val finished = CompletableDeferred<Unit>()
diff --git a/src/gateway/server-methods/talk.ts b/src/gateway/server-methods/talk.ts
index 33cb6d7f116..85f78e91b6a 100644
--- a/src/gateway/server-methods/talk.ts
+++ b/src/gateway/server-methods/talk.ts
@@ -112,83 +112,58 @@ function buildTalkTtsConfig(
     auto: "always",
     provider,
   };
+  const baseUrl = trimString(providerConfig.baseUrl);
+  const voiceId = trimString(providerConfig.voiceId);
+  const modelId = trimString(providerConfig.modelId);
+  const languageCode = trimString(providerConfig.languageCode);
 
   if (provider === "elevenlabs") {
+    const seed = finiteNumber(providerConfig.seed);
+    const applyTextNormalization = normalizeTextNormalization(
+      providerConfig.applyTextNormalization,
+    );
+    const voiceSettings = readTalkVoiceSettings(providerConfig);
     talkTts.elevenlabs = {
       ...baseTts.elevenlabs,
       ...(providerConfig.apiKey === undefined ? {} : { apiKey: providerConfig.apiKey }),
-      ...(trimString(providerConfig.baseUrl) == null
-        ? {}
-        : { baseUrl: trimString(providerConfig.baseUrl) }),
-      ...(trimString(providerConfig.voiceId) == null
-        ? {}
-        : { voiceId: trimString(providerConfig.voiceId) }),
-      ...(trimString(providerConfig.modelId) == null
-        ? {}
-        : { modelId: trimString(providerConfig.modelId) }),
-      ...(finiteNumber(providerConfig.seed) == null
-        ? {}
-        : { seed: finiteNumber(providerConfig.seed) }),
-      ...(normalizeTextNormalization(providerConfig.applyTextNormalization) == null
-        ? {}
-        : {
-            applyTextNormalization: normalizeTextNormalization(
-              providerConfig.applyTextNormalization,
-            ),
-          }),
-      ...(trimString(providerConfig.languageCode) == null
-        ? {}
-        : { languageCode: trimString(providerConfig.languageCode) }),
-      ...(readTalkVoiceSettings(providerConfig) == null
-        ? {}
-        : { voiceSettings: readTalkVoiceSettings(providerConfig) }),
+      ...(baseUrl == null ? {} : { baseUrl }),
+      ...(voiceId == null ? {} : { voiceId }),
+      ...(modelId == null ? {} : { modelId }),
+      ...(seed == null ? {} : { seed }),
+      ...(applyTextNormalization == null ? {} : { applyTextNormalization }),
+      ...(languageCode == null ? {} : { languageCode }),
+      ...(voiceSettings == null ? {} : { voiceSettings }),
     };
   } else if (provider === "openai") {
+    const speed = finiteNumber(providerConfig.speed);
+    const instructions = trimString(providerConfig.instructions);
     talkTts.openai = {
       ...baseTts.openai,
       ...(providerConfig.apiKey === undefined ? {} : { apiKey: providerConfig.apiKey }),
-      ...(trimString(providerConfig.baseUrl) == null
-        ? {}
-        : { baseUrl: trimString(providerConfig.baseUrl) }),
-      ...(trimString(providerConfig.modelId) == null
-        ? {}
-        : { model: trimString(providerConfig.modelId) }),
-      ...(trimString(providerConfig.voiceId) == null
-        ? {}
-        : { voice: trimString(providerConfig.voiceId) }),
-      ...(finiteNumber(providerConfig.speed) == null
-        ? {}
-        : { speed: finiteNumber(providerConfig.speed) }),
-      ...(trimString(providerConfig.instructions) == null
-        ? {}
-        : { instructions: trimString(providerConfig.instructions) }),
+      ...(baseUrl == null ? {} : { baseUrl }),
+      ...(modelId == null ? {} : { model: modelId }),
+      ...(voiceId == null ? {} : { voice: voiceId }),
+      ...(speed == null ? {} : { speed }),
+      ...(instructions == null ? {} : { instructions }),
     };
   } else if (provider === "microsoft") {
+    const outputFormat = trimString(providerConfig.outputFormat);
+    const pitch = trimString(providerConfig.pitch);
+    const rate = trimString(providerConfig.rate);
+    const volume = trimString(providerConfig.volume);
+    const proxy = trimString(providerConfig.proxy);
+    const timeoutMs = finiteNumber(providerConfig.timeoutMs);
     talkTts.microsoft = {
       ...baseTts.microsoft,
       enabled: true,
-      ...(trimString(providerConfig.voiceId) == null
-        ? {}
-        : { voice: trimString(providerConfig.voiceId) }),
-      ...(trimString(providerConfig.languageCode) == null
-        ? {}
-        : { lang: trimString(providerConfig.languageCode) }),
-      ...(trimString(providerConfig.outputFormat) == null
-        ? {}
-        : { outputFormat: trimString(providerConfig.outputFormat) }),
-      ...(trimString(providerConfig.pitch) == null
-        ? {}
-        : { pitch: trimString(providerConfig.pitch) }),
-      ...(trimString(providerConfig.rate) == null ? {} : { rate: trimString(providerConfig.rate) }),
-      ...(trimString(providerConfig.volume) == null
-        ? {}
-        : { volume: trimString(providerConfig.volume) }),
-      ...(trimString(providerConfig.proxy) == null
-        ? {}
-        : { proxy: trimString(providerConfig.proxy) }),
-      ...(finiteNumber(providerConfig.timeoutMs) == null
-        ? {}
-        : { timeoutMs: finiteNumber(providerConfig.timeoutMs) }),
+      ...(voiceId == null ? {} : { voice: voiceId }),
+      ...(languageCode == null ? {} : { lang: languageCode }),
+      ...(outputFormat == null ? {} : { outputFormat }),
+      ...(pitch == null ? {} : { pitch }),
+      ...(rate == null ? {} : { rate }),
+      ...(volume == null ? {} : { volume }),
+      ...(proxy == null ? {} : { proxy }),
+      ...(timeoutMs == null ? {} : { timeoutMs }),
     };
   } else {
     return { error: `talk.speak unavailable: unsupported talk provider '${resolved.provider}'` };