|
Gemini 3 Flash Preview via LiveKit Inference has much higher TTFT/jitter than direct Vertex in same Agents workflow
|
|
1
|
3
|
May 15, 2026
|
|
Anthropic Claude models in the agent builder
|
|
6
|
22
|
May 15, 2026
|
|
How does Azure gpt vs Open AI gpt has such latency difference?
|
|
2
|
32
|
May 13, 2026
|
|
Gpt-Realtime 2: Experience so far?
|
|
2
|
103
|
May 9, 2026
|
|
Livekit integration with langfuse
|
|
1
|
21
|
May 7, 2026
|
|
LLM Comparision
|
|
5
|
62
|
May 5, 2026
|
|
Whats your current go-to LLM model?
|
|
8
|
98
|
May 5, 2026
|
|
Handling response latency: Playing fallback/filler audio if no response arrives within a timeout
|
|
2
|
52
|
April 16, 2026
|
|
Gemini 3.1 Flash Lite Preview
|
|
2
|
59
|
April 3, 2026
|
|
How to configure serviceTier for AWS Bedrock voice agents
|
|
2
|
20
|
March 31, 2026
|
|
Critcal : AI Agent Unexpectedly Ending Interview Mid-Session
|
|
6
|
44
|
March 23, 2026
|
|
Agent handoff fails when tool returning Agent runs in parallel with reply-producing tool (pipeline path)
|
|
1
|
19
|
March 19, 2026
|
|
Assistance Needed:
|
|
6
|
55
|
March 16, 2026
|
|
Lowest latency STT/TTS/LLM stack for German - what's your experience?
|
|
1
|
67
|
March 13, 2026
|
|
Agent speaking audio_text tokens out loud
|
|
4
|
53
|
March 6, 2026
|
|
Using livekit.agents.llm.RealtimeModel with liteLLM
|
|
2
|
43
|
March 2, 2026
|
|
Achieving multi‑agent awareness and state synchronization with LiveKit Data Channels
|
|
3
|
92
|
February 24, 2026
|
|
Dangerous assistant turn merging with Gemini
|
|
1
|
21
|
February 20, 2026
|
|
Tool call started event
|
|
3
|
41
|
February 18, 2026
|
|
Qwen model speaking tool call JSON out loud instead of executing
|
|
1
|
16
|
January 21, 2026
|
|
Can I use my own API keys for external vendors (STT, TTS, LLM)?
|
|
1
|
10
|
January 21, 2026
|