From 303355eb16ea234413dbef375a141ed7976ac6b6 Mon Sep 17 00:00:00 2001 From: Sam Rolfe Date: Thu, 8 Oct 2026 22:06:28 +1100 Subject: [PATCH] sam-4screen-desktop 2026-10-8:22:6:28 --- .obsidian/workspace.json | 6 ++--- .trash/Untitled 20.md | 10 ++++++++ ...— Cloud STT and TTS with Local Fallback.md | 18 ++++++++++++--- 010 inbox/_sort log.md | 7 ++++++ .../Home Voice Assistant System.md | 23 +++++++++++++------ 5 files changed, 51 insertions(+), 13 deletions(-) create mode 100644 .trash/Untitled 20.md diff --git a/.obsidian/workspace.json b/.obsidian/workspace.json index bbadd2d..f0af77f 100644 --- a/.obsidian/workspace.json +++ b/.obsidian/workspace.json @@ -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", diff --git a/.trash/Untitled 20.md b/.trash/Untitled 20.md new file mode 100644 index 0000000..fe00eb7 --- /dev/null +++ b/.trash/Untitled 20.md @@ -0,0 +1,10 @@ +--- +created: 2026-10-08 21:57 +modified: 2026-10-08 21:57 +type: note +tags: [] +aliases: [] +--- +# [[Untitled]] + + diff --git a/010 inbox/MiniMax Voice — Cloud STT and TTS with Local Fallback.md b/010 inbox/MiniMax Voice — Cloud STT and TTS with Local Fallback.md index 90ba3de..e2f4e91 100644 --- a/010 inbox/MiniMax Voice — Cloud STT and TTS with Local Fallback.md +++ b/010 inbox/MiniMax Voice — Cloud STT and TTS with Local Fallback.md @@ -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) diff --git a/010 inbox/_sort log.md b/010 inbox/_sort log.md index b8dbdd1..f42b291 100644 --- a/010 inbox/_sort log.md +++ b/010 inbox/_sort log.md @@ -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) 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 4083918..8ef89b0 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 @@ -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).