sam/obsidian-vault
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

sam-4screen-desktop 2026-10-8:22:6:28

Browse Source
This commit is contained in:
Sam Rolfe
2026-10-08 22:06:28 +11:00
parent 057487f876
commit 303355eb16
5 changed files with 51 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
.obsidian/workspace.json vendored
View File

@@ -210,15 +210,16 @@
"templater-obsidian:Templater": false
}
},
"active": "8018aa52f0591df9",
"active": "26813e16e829b798",
"lastOpenFiles": [
"010 inbox/Untitled.md",
"000 daily/Daily Notes and To Do.md",
"010 inbox/MiniMax Voice — Cloud STT and TTS with Local Fallback.md",
"300 areas/355 AI Research and Techniques/Ai memory management.md",
"200 projects/Tools Software WebUI/Family Console.md",
"200 projects/Tools Software WebUI/Family Home Lab.md",
"300 areas/360 Dev-Ops Network Computers/Home Network Map Overview.md",
"300 areas/350 AI Pi Coding Agent/Pi Agent Extensions & Skills.md",
"000 daily/Daily Notes and To Do.md",
"300 areas/360 Dev-Ops Network Computers/Error Tracking.md",
"100 Table of Contents/Areas.md",
"300 areas/310 Home Assistant/Tuya Local Integration Notes.md",
@@ -239,7 +240,6 @@
"300 areas/395 AI Tools to try/AI Tools to try.md",
"400 Personal Family/410 Business Ideas/Business Ideas Display Screens.md",
"010 inbox/Business Idea - Franchises display screens.md",
"400 Personal Family/410 Business Ideas/Business Idea - Franchises display screens.md",
"010 inbox/_WATCHER",
"300 areas/355 AI Research and Techniques",
"300 areas/355 Ai Research and Techniques",

10
.trash/Untitled 20.md Normal file
View File

@@ -0,0 +1,10 @@
---
created: 2026-10-08 21:57
modified: 2026-10-08 21:57
type: note
tags: []
aliases: []
---
# [[Untitled]]

18
010 inbox/MiniMax Voice — Cloud STT and TTS with Local Fallback.md
View File

@@ -8,15 +8,14 @@ proposed_tags:
- migration
- home-assistant
- project
- esp32
- architecture
- minimax
- voice
- ai
- showcase
confidence: 0.66
confidence: 0.71
approved: false
proposed_for: 324fa7828911
proposed_for: 636ce731505f
created: "2026-10-08"
tags:
- project
@@ -86,6 +85,19 @@ flowchart LR
SNAP --> SPEAKERS[House speakers]
```
## 🏠 Home Assistant integration
Home Assistant announcements no longer call piper directly. `script.jervis_say`
publishes an instruction to MQTT `homeassistant/voice/announce`, and the agent
runs it in **announce mode** with **no tools**, so an announcement cannot trigger
a tool call. Voice reminders use the helper `input_text.voice_reminder_message`
(0–255 characters) and trigger on the `timer.finished` event, so cancelling a
timer is silent. The calendar reminder and `script.piper_tts_announcement` were
repointed from the missing `rest_command.jervis_say` onto `script.jervis_say`.
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.
## 🔗 Related Notes & Links
- Interactive Map: [Archify Map](https://maps.lab.audasmedia.com.au/minimax_voice_tts_stt/docs/minimax-voice-map.html)

7
010 inbox/_sort log.md
View File

@@ -20026,3 +20026,10 @@ What the watcher did, newest last.
### 2026-10-08 16:16:18
- **proposed** `MiniMax Voice — Cloud STT and TTS with Local Fallback.md` → `200 projects/Tools Software WebUI` (confidence 0.66)
### 2026-10-08 21:57:23
- **held** `Untitled.md` — BLOCKED: untitled notes are never moved automatically. Rename it first if it is real content.
### 2026-10-08 22:03:13
- **re-proposing** `MiniMax Voice — Cloud STT and TTS with Local Fallback.md` — you edited it
- **proposed** `MiniMax Voice — Cloud STT and TTS with Local Fallback.md` → `200 projects/Tools Software WebUI` (folder already set — kept) (confidence 0.71)

23
300 areas/360 Dev-Ops Network Computers/Home Voice Assistant System.md
View File

@@ -22,7 +22,7 @@ aliases:
> - **Tasks/progress:** see the Vikunja project; docs live in Outline; this note is the human map.
## What it is (TL;DR)
A private, local voice assistant. Say **"Hey Jervis"** (ESP32 wake word) then a natural-language request — a local **LLM agent** decides intent and calls tools: it controls Home Assistant, manages shopping/tasks/calendar, plays music, answers questions, and speaks back through the house speakers (piper → Snapcast).
A private, local voice assistant. Say **"Hey Jervis"** (ESP32 wake word) then a natural-language request — a local **LLM agent** decides intent and calls tools: it controls Home Assistant, manages shopping/tasks/calendar, plays music, answers questions, and speaks back through the house speakers (MiniMax T2A v2 via `tts_router`, with piper as the fallback → Snapcast).
**Command it from anywhere:** `POST http://192.168.20.13:8501/voice {"text": "add milk to the shopping list"}` — the reply is spoken.
@@ -31,8 +31,11 @@ Speech-to-text and text-to-speech now run on **MiniMax cloud APIs**, with a
**local fallback** so the house still works offline. Wake-word detection stays
local; only the spoken command is sent to the cloud.
- **STT**: `voice_stt_shim` (`:5001`) — cloud primary (OpenRouter `whisper-1`;
MiniMax `asr-1.0` ready), local `base.en` fallback (`:5002`).
- **STT**: `voice_stt_shim` (`:5001`) — cloud primary MiniMax `asr-1.0` on the
funded `MINIMAX_SUBSCRIPTION_KEY`, local `base.en` fallback (`:5002`). The
primary moved from OpenRouter `whisper-1` to MiniMax on 2026-10-08: MiniMax
tied OpenRouter on accuracy (WER 0.0151, 21/22 exact) and tripped the live 3 s
timeout 0/22 vs OpenRouter 4/22. Rollback is one compose line.
- **TTS**: `tts_router` behind the unchanged `speak_direct.sh` — MiniMax T2A v2
with piper fallback.
- **Personality**: the agent emits a speech plan (inline sound tags + one
@@ -48,7 +51,8 @@ ESP32 (wake word, mic) → MQTT voice/audio_stream
→ voice_bridge (OpenWakeWord, local)
→ voice_stt_shim (:5001) — cloud STT + local base.en fallback (:5002)
→ Jervis agent (FastAPI :8501, LLM tool-calling)
├─ Home Assistant (lights, timers, calendar, HA todo lists)
├─ Home Assistant (lights, timers, calendar, HA todo lists;
│ announcements via Jervis: script.jervis_say → MQTT voice/announce → announce mode, no tools)
├─ OmniRoute LLM (voice-fast: OpenRouter → opencode-go → deepseek flash)
├─ Mopidy → Spotify → Snapcast (music)
├─ Apprise (family WhatsApp/Telegram/ntfy/email)
@@ -68,15 +72,20 @@ ESP32 (wake word, mic) → MQTT voice/audio_stream
| OmniRoute | .13 | :20129 | LLM gateway (voice-fast route) |
| Home Assistant | .30 | :8123 | control, timers, calendar, todo lists |
| Mopidy + Spotify | .13 | :6600 / librespot | music |
| piper_tts | .13 | :10200 | TTS → Snapcast |
| piper_tts | .13 | :10200 | TTS fallback (piper) → Snapcast |
| Snapcast | .13 | :1780 | multi-room audio |
| Apprise | .35 | :8210 | notifications |
| Vikunja | .35 | vikunja.lab | project tasks/stages (tracker) |
| Outline | .13 | :3000 | project documentation (AI) |
## Status (2026-10-08)
- **Voice working end-to-end**: ESP32 wake word → whisper → agent → piper → Snapcast (fixed docker piper, HA→.13 SSH auth, resampler, MQTT client-id).
- **HA integration**: lights/scenes via Assist; shopping lists via HA todo (`add_shopping_item`); timers + spoken reminders (HA `timer` → automation → piper); calendar alerts spoken 30 min before (HA automation); add-calendar tool.
- **Voice working end-to-end**: ESP32 wake word → STT (`voice_stt_shim`, MiniMax `asr-1.0` primary + local `base.en` fallback) → agent → TTS (`tts_router`, MiniMax T2A v2 + piper fallback) → Snapcast (fixed docker piper, HA→.13 SSH auth, resampler, MQTT client-id).
- **HA integration**: lights/scenes via Assist; shopping lists via HA todo (`add_shopping_item`); timers + spoken reminders; calendar alerts spoken 30 min before; add-calendar tool.
- **HA announcements route through Jervis, not piper**: `script.jervis_say` publishes the instruction to MQTT `homeassistant/voice/announce`; the agent runs it in **announce mode** (`POST /announce`, `_run(text, announce=True)`) with **no tools at all**, so an announcement cannot trigger a tool call.
- **Voice reminders**: helper `input_text.voice_reminder_message` (0–255 chars) feeds `script.jervis_say`; `automation.voice_reminder_speak` now triggers on the `timer.finished` event, so cancelling a timer no longer announces.
- **Calendar + piper announcements**: `automation.speak_calendar_event_reminder_30_min_before` and `script.piper_tts_announcement` were repointed off the missing `rest_command.jervis_say` to `script.jervis_say`; the loaded action was proven with a WebSocket `trace/get`.
- **Doorbell TTS repaired**: `doorbell_tts_to_wav.sh` now uses the Docker piper plus `ffmpeg`; the old native piper and `sox` are gone.
- **Weather script**: `script.n8n_voice_query_weather` argument mismatch is fixed (`data.text` / `data.source`); the n8n weather webhook target is dead, so a weather query cannot complete through that script as written.
- **Music**: play/pause/skip/volume via Mopidy → Spotify → Snapcast (credentials.json device-auth).
- **Q&A + web search**: Tavily-backed `web_search`; fast LLM route `voice-fast` (~2–3s).
- **Family messaging**: Apprise (sam/finn/harry/joanna; WhatsApp/email/Telegram/ntfy).