修复(discord)：强化实时语音唤醒加入 · openclaw/openclaw@fdfcb07
steipete
·
2026-05-24
·
via Recent Commits to openclaw:main
| 原文行号 | 差异行号 | 差异行变 |
|---|
@@ -1234,7 +1234,7 @@ Notes:
|
1234 | 1234 | - In `stt-tts` mode, STT uses `tools.media.audio`; `voice.model` does not affect transcription. |
1235 | 1235 | - In realtime modes, `voice.realtime.provider`, `voice.realtime.model`, and `voice.realtime.voice` configure the realtime audio session. For OpenAI Realtime 2 plus the Codex brain, use `voice.realtime.model: "gpt-realtime-2"` and `voice.model: "openai-codex/gpt-5.5"`. |
1236 | 1236 | - Realtime voice modes include small `IDENTITY.md`, `USER.md`, and `SOUL.md` profile files in the realtime provider instructions by default so fast direct turns keep the same identity, user grounding, and persona as the routed OpenClaw agent. Set `voice.realtime.bootstrapContextFiles` to a subset to customize this, or `[]` to disable it. The supported realtime bootstrap files are limited to those profile files; `AGENTS.md` stays in the normal agent context. The injected profile context does not replace `openclaw_agent_consult` for workspace work, current facts, memory lookup, or tool-backed actions. |
1237 | | -- In OpenAI `agent-proxy` realtime mode, set `voice.realtime.requireWakeName: true` to keep Discord realtime voice silent until a transcript contains a wake name. If `voice.realtime.wakeNames` is unset, OpenClaw uses the routed agent `name`, falling back to the agent id. Wake-name gating disables realtime provider auto-response and routes accepted turns through the OpenClaw agent consult path. |
| 1237 | +- In OpenAI `agent-proxy` realtime mode, set `voice.realtime.requireWakeName: true` to keep Discord realtime voice silent until a transcript contains a wake name. If `voice.realtime.wakeNames` is unset, OpenClaw uses the routed agent `name` plus `OpenClaw`, falling back to the agent id plus `OpenClaw`. Wake-name gating disables realtime provider auto-response and routes accepted turns through the OpenClaw agent consult path. |
1238 | 1238 | - The OpenAI realtime provider accepts current Realtime 2 event names and legacy Codex-compatible aliases for output audio and transcript events, so compatible provider snapshots can drift without dropping assistant audio. |
1239 | 1239 | - `voice.realtime.bargeIn` controls whether Discord speaker-start events interrupt active realtime playback. If unset, it follows the realtime provider's input-audio interruption setting. |
1240 | 1240 | - `voice.realtime.minBargeInAudioEndMs` controls the minimum assistant playback duration before an OpenAI realtime barge-in truncates audio. Default: `250`. Set `0` for immediate interruption in low-echo rooms, or raise it for echo-heavy speaker setups. |
|
此內容由慣性聚合(RSS閱讀器)自動聚合整理，僅供閱讀參考。 原文來自 — 版權歸原作者所有。
