|
Issue: RealtimeModelMetrics.ttft is always logged as 0.0 for gemini 3.8 live on vertex ai
|
|
2
|
31
|
October 7, 2026
|
|
Gemini-3.8-live rejected with vertexai=True in livekit-plugins-google, although Vertex AI serves it (EU multi-region)
|
|
7
|
74
|
October 6, 2026
|
|
Per-session CPU burst from a plugin's native model being built lazily on the first audio frame (AI_Cousitcs) — any pattern for prewarmable per-session init?
|
|
0
|
17
|
October 2, 2026
|
|
Was it us or them? Answering "the live froze for me" with evidence
|
|
3
|
24
|
October 1, 2026
|
|
Turn-taking on real SIP calls: what cut my median reply from 2.44 s to 1.81 s (plus a question on short answers)
|
|
2
|
28
|
September 29, 2026
|
|
Voice Live API connector
|
|
9
|
180
|
September 23, 2026
|
|
Gemini Realtime API error: 1007 None. The audio content type (CONTENT_TYPE_AUDIO) is not supported for this model
|
|
6
|
207
|
September 18, 2026
|
|
OpenAI Realtime STT metrics recorded in Livekit
|
|
2
|
51
|
September 17, 2026
|
|
Self-hosted LiveKit for a university, which cloud/bare-metal provider fits this bandwidth-heavy load?
|
|
3
|
104
|
September 7, 2026
|
|
Data residency of South African sensitive data -
|
|
4
|
40
|
September 4, 2026
|
|
Agent shows persistent "ERROR" status — zero dispatch attempts logged, spanning multiple hours
|
|
9
|
85
|
August 31, 2026
|
|
Inaccurate Transcript Despite Correct Realtime Understanding
|
|
23
|
233
|
August 27, 2026
|
|
Unity Android Voice Chat Issues (Playback Route, Bluetooth, Samsung Low Microphone Volume)
|
|
17
|
180
|
August 24, 2026
|
|
Agent didn't followup after tool call
|
|
9
|
157
|
August 12, 2026
|
|
PSA: the FrameProcessor resample pattern silently discards ~16% of caller audio
|
|
4
|
49
|
August 11, 2026
|
|
How to size self-hosted LiveKit for 200 concurrent classrooms × 50 participants (10,000 total) — what hardware/config do I need?
|
|
0
|
115
|
July 31, 2026
|
|
Seeking strategies to optimize connection reliability and audio quality for users in strict GCC network environments experiencing aggressive UDP throttling
|
|
18
|
235
|
July 28, 2026
|
|
Gemini Realtime API error: 1007 None. The audio content type (CONTENT_TYPE_AUDIO) is not supported for this model configuration
|
|
3
|
127
|
July 27, 2026
|
|
Proposed enhancements for livekit.agents.llm.RealtimeModelFallbackAdapter
|
|
0
|
31
|
July 27, 2026
|
|
AWS Nova Sonic RealtimeModel (amazon.nova-2-sonic-v1:0): metrics emitted repeatedly and ttftalways0.0
|
|
2
|
44
|
July 21, 2026
|
|
I put LiveKit on an ESP32-S3 + ReSpeaker XVF3800 — a full-duplex smart speaker that listens while it talks
|
|
16
|
258
|
July 9, 2026
|
|
Bugs and proposed enhancements related to the generate_reply timeout following up actions
|
|
3
|
82
|
June 29, 2026
|
|
Payload type filtering
|
|
2
|
74
|
June 29, 2026
|
|
Generate reply timeout for gemini-live-2.5-flash-native-audio realtime model
|
|
2
|
79
|
June 28, 2026
|
|
Livekit Gemini-Live Pause issue
|
|
9
|
219
|
June 19, 2026
|
|
Audio Intelligence for Voice Agents
|
|
1
|
97
|
June 19, 2026
|
|
LiveKit Cloud GStreamer Pipeline Crashing with Connection Timeout (~4 min mark)
|
|
3
|
198
|
June 18, 2026
|
|
Session.say() hangs indefinitely (~20s+) when using Gemini RealtimeModel(gemini 3.1) as llm together with google.beta.GeminiTTS as tts; session.input.set_audio_enabled() / aec_warmup_duration do not reliably block user interruption in this configuration
|
|
3
|
84
|
June 18, 2026
|
|
Realtime model is not working properly
|
|
8
|
153
|
May 30, 2026
|
|
Improving accuracy
|
|
6
|
163
|
May 26, 2026
|