From a5c60d0dfcbc70ac65b8eb2304567497511f3ace Mon Sep 17 00:00:00 2001
From: Sam Rolfe <samuelrolfe@gmail.com>
Date: Fri, 16 Oct 2026 18:21:28 +1100
Subject: [PATCH] sam-4screen-desktop 2026-10-16:18:21:28

---
 ...e — Cloud STT and TTS with Local Fallback.md | 17 +++++++++++++++--
 .../Home Voice Assistant System.md              | 14 ++++++++++----
 2 files changed, 25 insertions(+), 6 deletions(-)

diff --git a/200 projects/Tools Software WebUI/MiniMax Voice — Cloud STT and TTS with Local Fallback.md b/200 projects/Tools Software WebUI/MiniMax Voice — Cloud STT and TTS with Local Fallback.md
index 9c82d66..25c3924 100644
--- a/200 projects/Tools Software WebUI/MiniMax Voice — Cloud STT and TTS with Local Fallback.md	
+++ b/200 projects/Tools Software WebUI/MiniMax Voice — Cloud STT and TTS with Local Fallback.md	
@@ -3,7 +3,7 @@ title: MiniMax Voice
 type: project
 status: active
 created: "2026-10-08"
-updated: "2026-09-26"
+updated: "2026-10-16"
 tags:
   - migration
   - home-assistant
@@ -89,12 +89,25 @@ The doorbell script `doorbell_tts_to_wav.sh` now uses the Docker piper plus
 `ffmpeg`. The live STT primary is MiniMax `asr-1.0` on the funded
 `MINIMAX_SUBSCRIPTION_KEY`, with the local `base.en` fallback unchanged.
 
+## 🎙 Voice rotation
+
+Jervis picks the voice for each spoken reply from a **13-voice shuffle bag**
+(`tts_router/speech_plan.py` → `MINIMAX_VOICES`). The voice is random and
+decoupled from mood: every voice is drawn once per 13-reply cycle, with no
+back-to-back repeat. The bag is held in process memory, so it refills when
+`voice-agent` restarts.
+
+The newest member (2026-10-16) is **Aussie Sam**, a MiniMax instant clone. Its
+API id is `moss_audio_4b669dff-c927-11f1-9228-82eadf641028`; the aliases
+`aussie sam` and `moss` resolve to it. Live `t2a_v2` synthesis is verified. Add
+a future voice the same way, then restart the agent to load it.
+
 ## 🔗 Related Notes & Links
 
 - Interactive Map: [Archify Map](https://maps.lab.audasmedia.com.au/minimax_voice_tts_stt/docs/minimax-voice-map.html)
 - Project workspace: `/home/sam/paseo/projects/minimax_voice_tts_stt/` on `.13`
 - Vikunja: *Jervis Voice Assistant (Whisper ESP HA Flow)* project
-- Outline: *Voice Assistant (Whisper ESP HA)* collection
+- Outline: *MiniMax Voice (STT + TTS)* collection
 - Related: [[Home Voice Assistant System]]
 
 <!--
diff --git a/300 areas/360 Dev-Ops Network Computers/Home Voice Assistant System.md b/300 areas/360 Dev-Ops Network Computers/Home Voice Assistant System.md
index 8ef89b0..5eb4dcd 100644
--- a/300 areas/360 Dev-Ops Network Computers/Home Voice Assistant System.md	
+++ b/300 areas/360 Dev-Ops Network Computers/Home Voice Assistant System.md	
@@ -1,6 +1,6 @@
 ---
 created: 2026-08-30
-modified: 2026-10-08
+modified: 2026-10-16
 type: area
 status: active
 tags:
@@ -17,7 +17,7 @@ aliases:
 
 > **Human-readable overview of the local voice-assistant project.**
 > - **AI/project tracking:** Vikunja → *Jervis Voice Assistant (Whisper ESP HA Flow)* (project id 5)
-> - **AI documentation (for bots):** Outline → *Voice Assistant (Whisper ESP HA)* collection → [Project Overview](/doc/project-overview-genev9IHFT)
+> - **AI documentation (for bots):** Outline → *MiniMax Voice (STT + TTS)* collection
 > - **API/docs (Gitea):** `sam/voice-assistant` → overview / agent-api / clients
 > - **Tasks/progress:** see the Vikunja project; docs live in Outline; this note is the human map.
 
@@ -40,6 +40,12 @@ local; only the spoken command is sent to the cloud.
   with piper fallback.
 - **Personality**: the agent emits a speech plan (inline sound tags + one
   emotion/delivery config). Kill switch: `VOICE_PERSONALITY=0`.
+- **Voice rotation**: Jervis draws each reply's voice from a **13-voice shuffle
+  bag** (`tts_router/speech_plan.py` → `MINIMAX_VOICES`); the voice is random and
+  decoupled from mood, one per cycle with no back-to-back repeat. Newest member
+  is **Aussie Sam**, an instant clone (`moss_audio_4b669dff-c927-11f1-9228-82eadf641028`)
+  added 2026-10-16. The bag is in process memory, so a `voice-agent` restart
+  loads it.
 - **Result**: about 239 MiB of resident RAM freed, better voices, and voice
   input survives an internet outage.
 - Full project note: [[MiniMax Voice — Cloud STT and TTS with Local Fallback]].
@@ -96,9 +102,9 @@ FastAPI · Python · Docker · MQTT · Home Assistant (REST/Assist/automations)
 
 ## Key configs & links
 - **Vikunja project**: `https://vikunja.lab.audasmedia.com.au` → *Jervis Voice Assistant (Whisper ESP HA Flow)*
-- **Outline collection**: `https://outline.lab.audasmedia.com.au` → *Voice Assistant (Whisper ESP HA)*
+- **Outline collection**: `https://outline.lab.audasmedia.com.au` → *MiniMax Voice (STT + TTS)*
 - **MiniMax Voice project**: `/home/sam/paseo/projects/minimax_voice_tts_stt/` on `.13`; map at `https://maps.lab.audasmedia.com.au/minimax_voice_tts_stt/docs/`
-- **Gitea**: `sam/voice-assistant` (overview / agent-api / clients docs)
+- **Gitea**: `sam/minimax_voice_tts_stt` (this project) and `sam/voice-assistant` (overview / agent-api / clients docs)
 - **Repo layout / plan**: `~/chats/homeassistant` (plan.md, AGENT.md); agent at `/home/sam/voice-agent/`
 - **Secrets**: `~/.config/environment.d/10-secrets.conf` on .27/.13/.51 (VIKUNJA_TOKEN, OL_API_KEY, etc.) — see also the `secrets_fixes` note.