isair/jarvis

Task 1b — Speak "I didn't quite catch that" via TTS on low confidence

Open

#374 geöffnet am 5. Mai 2026

Auf GitHub ansehen
 (0 Kommentare) (0 Reaktionen) (0 zugewiesene Personen)Python (201 Forks)github user discovery
enhancementgood first issue

Repository-Metriken

Stars
 (1.090 Stars)
PR-Merge-Metriken
 (Durchschn. Merge 1T 12h) (19 gemergte PRs in 30 T)

Beschreibung

Task 1b — TTS response for low-confidence transcript

Part of Task 1: Low Confidence Voice Feedback. Depends on #373 (Task 1a).

What to do

Using the low-confidence event surfaced in Task 1a, trigger a TTS response when Whisper confidence falls below the rejection threshold.

  • In src/jarvis/reply/ or wherever the listener dispatches results, handle the low-confidence event.
  • Call the TTS engine (in src/jarvis/output/) to say a short phrase such as "I didn't quite catch that" or "Sorry, could you repeat that?".
  • The phrase should ideally be a constant or config value, not hardcoded inline.
  • Do not speak this if Jarvis is already speaking or in cooldown (respect existing TTS guard logic).

Files to touch

  • src/jarvis/reply/ (dispatch/handler)
  • src/jarvis/output/tts.py (if a new helper method is needed)

Acceptance criteria

  • Jarvis speaks an audible response when confidence is too low
  • Response phrase is a named constant (not a magic string inline)
  • Does not double-speak if TTS is already active
  • No TTS triggered for normal successful transcripts

Contributor Guide