connection lost — retrying
RoboPark Control
connecting…
--robots online
--attention
Voice stack STTLLMTTS
set operator
Production command center

Fleet intelligence

Live readiness, workload, release compliance, hardware pressure, and operator actions across every RoboPark device.

Operational readinesslive
Robot workloadsessions / triggers
Needs attention0 issues

Fleet

hub robot peer dispatch telemetry
drag to pan · scroll to zoom · click a robot for cam / mic / speaker · ctrl+drag a robot to reposition (persists)
🤖
robot
satellite
idle

RoboPark · sessions & telemetry

Fleet health · sessions (last 60 min) —

Top robots by activity
Recent activity last 20
Visual operations

Fleet camera grid

Loading camera-capable robots…
Hardware operations

Per-robot motor control and testing

Controls mirror each robot's registered motor-server relays. Unknown GPIO outputs are never exposed or pulsed.
Loading registered relay capabilities…
Production conversations camera · pipeline · transcript
Waiting for active production conversations
RobotSessionStartedDurationEnd reasonActions
RoboVoice operator channel
Royal Voice Studio
No active session
CAMERA
Ready when you areselect character and begin
ready to start00:00
--Total response
--STT to LLM
--LLM to TTS
System Voice pipeline is standing by.
Conversation0 messages
Your live transcript and typed messages appear here.
Durable voice archive

Cross-engine session transcripts

RoboVoice and ElevenLabs history with persistent labels and full transcripts.

SessionRobotEngineAgent / stackModelStartedDurationTurnsLabelsActions
—
All 🤖 Robot 📡 Device 🎙 Session 🖥 Server 🗣 Voice 🎭 Character
👤 by me
TimeCategoryActionTargetDetailsOperator
Liveness polling mesh + scheduler + devices
mesh
—
awaiting first poll…
scheduler
—
awaiting first poll…
cameras
—
awaiting first session…
production mode
—
awaiting first poll…
Active incidents 0
All ✗ critical ⚠ warning · info
no active incidents
Acknowledged 0
no acknowledged incidents
incidents are derived from /api/telemetry readiness codes. Acknowledgments are stored in your browser (localStorage) so multiple operators on different machines each get their own list. When a robot's readiness returns to "ready" or "in_session" the incident auto-closes.
Operational readinessscheduler
Robot workloadsessions / triggers
Needs attention0 issues
Robots live + idle + offline

Voice provider secret

not configured · cached voice speaker tests require this key

Add LiveKit server

Advanced — ID, URL, credentials, capacity

Add robot (mint enrollment token)

the robot self-reports its IP and hardware on first heartbeat — you only need a name and (optionally) a character preset to get started.
Advanced — pre-set network/voice config before the robot connects

Runtime health · scheduler · LiveKit · Docker

not checked
ContainerStateImageActions
Docker controls are protected by the hub token. Logs are limited to the latest 100 lines.

RoboPark Easy Setup

Set up or repair a complete robot in about one minute. Choose three things, copy one command, and paste it on the robot.

Guided robot setup

One command. Complete production runtime.

The command installs RoboPark, removes the old supervised process safely, and starts camera, microphone, speaker, motion detection, motors, RoboVoice, and remote management.

ABOUT 1 MINUTE
Step 1Select the physical robot by name and exact ID; its immutable device ID is filled automatically.
Step 2Only real character presets appear here.
Step 3Only one engine owns the microphone and speaker at a time.
Step 4Choose LAN when the robot is onsite.
OptionalShown in fleet and session history.
Checking setup...
1Open Terminal on the Raspberry Pi.
2Paste the copied command and press Enter.
3Wait for enabled and started systemd unit. The robot then appears in Fleet.
Advanced tools, addresses, diagnostics, and recovery
The API key stays in ELEVENLABS_API_KEY on the robot.

Add a persistent command

Saved only in this operator browser.

Character & Voice Studio

Build reusable personas and production voice pipelines in one place. Changes are applied centrally and become available immediately in Voice Studio, Fleet, and every Park robot panel.

VOX

Voice stacks

Speech recognition, language model, synthesis, turn-taking, and wake behavior.

0 stacks
AI

Character presets

Persona, prompt, robot avatar, park placement, motors, and default voice stack.

0 presets
RAG

Shared Character Knowledge

Reusable Markdown and plain-text facts shared across selected characters, with server-side Ollama Cloud assistance.

0 docs
Library
Loading knowledge…
Document editor
Select or create a document
AI writing assistantchecking…
Ask me to draft, rewrite, summarize, or check this knowledge. Relevant library passages are retrieved automatically.