diff --git a/.openclaw-sync/source.json b/.openclaw-sync/source.json
index 5b066e4fd..91281eacd 100644
--- a/.openclaw-sync/source.json
+++ b/.openclaw-sync/source.json
@@ -1,5 +1,5 @@
 {
   "repository": "openclaw/openclaw",
-  "sha": "f9bb6e351519e0952c0bd7c25262e1806dcdc609",
-  "syncedAt": "2026-05-01T10:05:44.648Z"
+  "sha": "3585d3e22656c682585ff36707f90fb46769a1e8",
+  "syncedAt": "2026-05-01T10:20:37.413Z"
 }
diff --git a/docs/channels/discord.md b/docs/channels/discord.md
index e0883caa8..f4b365ebc 100644
--- a/docs/channels/discord.md
+++ b/docs/channels/discord.md
@@ -1063,6 +1063,7 @@ Notes:
 - `voice.tts` overrides `messages.tts` for voice playback only.
 - `voice.model` overrides the LLM used for Discord voice channel responses only. Leave it unset to inherit the routed agent model.
 - STT uses `tools.media.audio`; `voice.model` does not affect transcription.
+- Per-channel Discord `systemPrompt` overrides apply to voice transcript turns for that voice channel.
 - Voice transcript turns derive owner status from Discord `allowFrom` (or `dm.allowFrom`); non-owner speakers cannot access owner-only tools (for example `gateway` and `cron`).
 - Voice is enabled by default; set `channels.discord.voice.enabled=false` to disable voice runtime and the `GuildVoiceStates` gateway intent.
 - `channels.discord.intents.voiceStates` can explicitly override voice-state intent subscription. Leave it unset for the intent to follow `voice.enabled`.