Skip to content

Instantly share code, notes, and snippets.

@fortuna

fortuna/voice_assistant events.md

Last active June 8, 2025 19:28
Show Gist options
  • Save fortuna/41b40d808693348789156c523463ec21 to your computer and use it in GitHub Desktop.
Save fortuna/41b40d808693348789156c523463ec21 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
voice_assistant events.md
  1. VOICE_ASSISTANT_RUN_START - 1
    1. on_start
    2. VOICE_ASSISTANT_WAKE_WORD_START - 9
    3. — Listening here —
    4. VOICE_ASSISTANT_WAKE_WORD_END - 10
    5. on_wake_word_detected
    6. VOICE_ASSISTANT_STT_START - 3
      1. — After wake word —
      2. VOICE_ASSISTANT_STT_VAD_START - 11
      3. VOICE_ASSISTANT_STT_VAD_END - 12
    7. VOICE_ASSISTANT_STT_END - 4
    8. VOICE_ASSISTANT_INTENT_START - 5
    9. on_intent_start
    10. VOICE_ASSISTANT_INTENT_END - 6
    11. on_intent_end
    12. VOICE_ASSISTANT_TTS_START - 7
    13. on_tts_started
    14. VOICE_ASSISTANT_TTS_END - 8
    15. on_tts_end - Media URL is available
  2. VOICE_ASSISTANT_RUN_END - 2
  3. on_end
  4. – Response streaming —
  5. on_idle
@fortuna
Copy link
Author

fortuna commented Jun 8, 2025 •
edited
Loading

It's surprising that the response streaming starts after on_end, and the speaker is only released after on_idle.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment