Command Palette

Search for a command to run...

Live demo
You are browsing real pipeline data captured from a live 5-Domia home mesh — latencies, delegation journeys, memories and emotions are genuine. Voices are synthetic. The demo is read-only.
Conversations
Marlowe
Marlowe

Sep 29, 01:45 · session e3c573c2-5530-4483-acf2-cb3416d37d2d

Turn 2 of 4Full session
VOICEvoice
Pipeline
Mmarloweran the full pipeline locally
Total 586 msTTFA 586 ms

Wake word

kws-zipformer-gigaspeech
“computer”detected · session opened

Captured audio

User audio (input)11 KB
0:00 / 0:00

Speech-to-text

parakeet-tdt-06b-v273 ms

Turn the volume down.

Intent gate

0 ms

Routed to fast-path:music-assistant__volume_volume_down

Tool call

4 ms
music-assistant
music-assistant__volume_volume_downOK4 ms

Living Room volume is 40

LLM prompt

—

LLM response

llama3.2:3b

Turning it down.

1 toolheard 1.4s

Text-to-speech

KOKORO · am_michael508 ms
TTS output · KOKORO9 KB
0:00 / 0:00
Perceived latency
Archived copy

Speech end to audible reply

5 ms

  • Transcript final+0 ms—
  • First TTS unit+5 ms5 ms

Not recorded: Speech end, First LLM token, Audio audible

End of utterance—Transcription delay—Fast path0 msEndpoint debounce—

Also recorded

Agent tools4 ms
Turn timeline
  1. Turn started+0 ms
  2. Speech recognized+80 ms

    Turn the volume down.

  3. Tool requested+81 ms
    music-assistant__volume_volume_down
  4. tool.started+82 ms
  5. Tool result+85 ms
    music-assistant__volume_volume_downoktool 4 ms
  6. Intent decided+85 ms
    fast-path:music-assistant__volume_volume_down
  7. Turn completed+596 ms
    ttfa 586 mstotal 586 ms
Tool runs

Every tool this turn dispatched, with the policy that let it through.

archived
music-assistant__volume_volume_downOKrisk write_additiveallow · risk_default2 ms
music-assistant1 month ago
Replay
586 ms
0:00 / 0:01
Speech-to-text73 ms12%
Text-to-speech508 ms87%
Time to first audio586 ms
Run again

Re-running needs a live mesh — disabled in this read-only demo.

Evaluation
Domia state

Marlowe

ANALYTICALARTISTSARCASTICADULT

STT parakeet-tdt-06b-v2

LLM llama3.2:3b

TTS KOKORO

voice am_michael