From 51d759dc87df23776385238b00972a5ba2b36b3d Mon Sep 17 00:00:00 2001 From: "openclaw-docs-sync[bot]" Date: Fri, 1 May 2026 10:07:37 +0000 Subject: [PATCH] chore(sync): mirror docs from openclaw/openclaw@f9bb6e351519e0952c0bd7c25262e1806dcdc609 --- .openclaw-sync/source.json | 4 ++-- docs/channels/discord.md | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/.openclaw-sync/source.json b/.openclaw-sync/source.json index ba6af1644..5b066e4fd 100644 --- a/.openclaw-sync/source.json +++ b/.openclaw-sync/source.json @@ -1,5 +1,5 @@ { "repository": "openclaw/openclaw", - "sha": "7ddf28c0d4403599cb788d0ad94c1b7fd87da622", - "syncedAt": "2026-05-01T10:00:24.653Z" + "sha": "f9bb6e351519e0952c0bd7c25262e1806dcdc609", + "syncedAt": "2026-05-01T10:05:44.648Z" } diff --git a/docs/channels/discord.md b/docs/channels/discord.md index a3b3daa0e..e0883caa8 100644 --- a/docs/channels/discord.md +++ b/docs/channels/discord.md @@ -1075,7 +1075,7 @@ Voice channel pipeline: - Discord PCM capture is converted to a WAV temp file. - `tools.media.audio` handles STT, for example `openai/gpt-4o-mini-transcribe`. -- The transcript is sent through normal Discord ingress and routing. +- The transcript is sent through Discord ingress and routing while the response LLM runs with a voice-output policy that hides the agent `tts` tool and asks for returned text, because Discord voice owns final TTS playback. - `voice.model`, when set, overrides only the response LLM for this voice-channel turn. - `voice.tts` is merged over `messages.tts`; the resulting audio is played in the joined channel.