From 769b66f57e567cdcc00d5d84a62d9e24d718178e Mon Sep 17 00:00:00 2001
From: Hoan Luu Huu <110280845+xquanluu@users.noreply.github.com>
Date: Thu, 20 Nov 2025 07:00:44 +0700
Subject: [PATCH] fixed playbackIds is not in correct order compare with
 say.text array (#1439)

* fixed playbackIds is not in correct order compare with say.text array

* wip

* wip
---
 lib/tasks/tts-task.js | 31 +++++++++++++++++++++----------
 1 file changed, 21 insertions(+), 10 deletions(-)

diff --git a/lib/tasks/tts-task.js b/lib/tasks/tts-task.js
index 3dc6e716..2663005c 100644
--- a/lib/tasks/tts-task.js
+++ b/lib/tasks/tts-task.js
@@ -279,9 +279,9 @@ class TtsTask extends Task {
       }
 
       /* produce an audio segment from the provided text */
-      const generateAudio = async(text) => {
-        if (this.killed) return;
-        if (text.startsWith('silence_stream://')) return text;
+      const generateAudio = async(text, index) => {
+        if (this.killed) return {index, filePath: null};
+        if (text.startsWith('silence_stream://')) return {index, filePath: text};
 
         /* otel: trace time for tts */
         if (!preCache && !this._disableTracing)  {
@@ -310,7 +310,6 @@ class TtsTask extends Task {
             renderForCaching: preCache
           });
           if (!filePath.startsWith('say:')) {
-            this.playbackIds.push(null);
             this.logger.debug(`Say: file ${filePath}, served from cache ${servedFromCache}`);
             if (filePath) cs.trackTmpFile(filePath);
             if (this.otelSpan) {
@@ -338,10 +337,11 @@ class TtsTask extends Task {
                 'id': this.id
               });
             }
+            return {index, filePath, playbackId: null};
           }
           else {
-            this.playbackIds.push(extractPlaybackId(filePath));
-            this.logger.debug({playbackIds: this.playbackIds}, 'Say: a streaming tts api will be used');
+            const playbackId = extractPlaybackId(filePath);
+            this.logger.debug('Say: a streaming tts api will be used');
             const modifiedPath = filePath.replace('say:{', `say:{session-uuid=${ep.uuid},`);
             this.notifyStatus({
               event: 'synthesized-audio',
@@ -350,9 +350,8 @@ class TtsTask extends Task {
               servedFromCache,
               'id': this.id
             });
-            return modifiedPath;
+            return {index, filePath: modifiedPath, playbackId};
           }
-          return filePath;
         } catch (err) {
           this.logger.info({err}, 'Error synthesizing tts');
           if (this.otelSpan) this.otelSpan.end();
@@ -367,8 +366,20 @@ class TtsTask extends Task {
         }
       };
 
-      const arr = this.text.map((t) => (this._validateURL(t) ? t : generateAudio(t)));
-      return (await Promise.all(arr)).filter((fp) => fp && fp.length);
+      // process all text segments in parallel will cause ordering issue
+      // so we attach index to each promise result and sort them later
+
+      const arr = this.text.map((t, index) => (this._validateURL(t) ?
+        Promise.resolve({index, filePath: t, playbackId: null}) : generateAudio(t, index)));
+      const results = await Promise.all(arr);
+      const sorted = results.sort((a, b) => a.index - b.index);
+
+      return sorted
+        .filter((fp) => fp.filePath && fp.filePath.length)
+        .map((r) => {
+          this.playbackIds.push(r.playbackId);
+          return r.filePath;
+        });
     } catch (err) {
       this.logger.info(err, 'TaskSay:exec error');
       throw err;