Files
matrix-ai-agent/voice.py
Christian Gick 1e1911995f fix(stt): filter ElevenLabs noise annotations before LLM
scribe_v2_realtime annotates background audio as *Störgeräusche*,
*Fernsehgeräusche* etc. Override stt_node to drop these so the LLM
only receives actual speech transcripts.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-22 17:59:17 +02:00

32 KiB