Issue: ElevenLabs inference.STT() outputs wrong language script (Malayalam) when speaking English When speaking clearly in English, the transcription comes back in Malayalam script (Indian language). Configuration:

stt=inference.STT(model="elevenlabs/scribe_v2_realtime", language="en")

SDK Version: livekit-agents 1.3.7 Example Debug Output:

transcript='ഹലോ കെന്യൂ ഹിയർ മി ഐ സെഡ്' is_final=False language='en'

The text

ഹലോ കെന്യൂ ഹിയർ മി ഐ സെഡ്

is Malayalam script that phonetically reads "hello can you hear me I said" - so ElevenLabs is hearing the English correctly but outputting it in the wrong script. Important: Deepgram via

inference.STT(model="deepgram/nova-3", language="en")

works perfectly with the exact same setup. The issue is specific to ElevenLabs through the inference layer. I saw issue #4255 mentioning a fix for how

scribe_v2_realtime

model name is sent to providers. Has this fix been released? I'm on 1.3.7 and still experiencing this issue.

Have you asked ElevenLabs about this?

no reply, and i think the bug is in LiveKits inference layer, not ElevenLabs. Proof:`inference.STT(model="deepgram/nova-3")` → WORKS PERFECTLY

elevenlabs.STT()

plugin directly → WORKS PERFECTLY

inference.STT(model="elevenlabs/scribe_v2_realtime")

→ BROKEN (outputs Santali, Malayalam, Punjabi instead of English) Same ElevenLabs account, same API key. The only difference is going through your inference addon vs the direct plugin. ElevenLabs is correctly transcribing when I bypass your inference layer. The bug is in how LiveKit's inference addon communicates with ElevenLabs - likely still sending incorrect model names or parameters despite issue #4255. I'm on

livekit-agents==1.3.8

(released today) and still getting hallucinations.

Thank you for raising this, we have the same problem. Have you found a solution?