Blog
Page 6 of 32
LiveKit Call Recording and Pipecat Audio Recording: Stereo Recordings, Egress and Per-Call Metrics
Record LiveKit and Pipecat calls in stereo: Egress channel routing, AudioBufferProcessor, Twilio dual-channel, clock alignment, storage math, metric code.
Running LiveKit Agents on Kubernetes: Scaling, Draining Calls and Safe Releases
LiveKit agent Kubernetes guide: how agent servers decide they're full, cgroup load traps, drain math for live calls, job-based autoscaling, safe canaries.
LiveKit Noise Cancellation Self-Hosted: Krisp, BVC, AEC and How to Test Them
What runs on self-hosted LiveKit for noise and echo: Krisp, BVC, open-source filters, AEC warmup, and a test plan with SNR beds, WER and barge-in rates.
Measuring Pipecat Latency Stage by Stage: Metrics, Observers and the Numbers That Lie
Measure Pipecat latency stage by stage: what each TTFB times, how UserBotLatencyObserver splits a turn, and how to check it against a call recording.
Deepgram Flux vs Silero VAD vs a Turn-Detector Model: Which End of Turn Detection Voice Agent Method to Use
Silence timers, Deepgram Flux, LiveKit and Smart Turn models, and semantic VAD compared: defaults, published benchmarks, the stacking trap, and a test.
LiveKit Transfer Call and Pipecat Handoff Guide: Ending Calls, Warm vs Cold Transfer, SIP REFER vs Bridge
How to end, cold-transfer and warm-transfer calls in LiveKit and Pipecat: SIP REFER vs bridge, real per-minute costs, failure modes and a test matrix.
OpenAI Realtime API SIP vs a Media-Stream Bridge: Putting OpenAI Realtime, GPT-Live, or Gemini Live on a Phone Line
OpenAI Realtime API SIP vs a Twilio media-stream bridge vs LiveKit or Pipecat: barge-in truncation, Gemini Live limits, DTMF, transfers, costs, and tests.
LiveKit vs Pipecat vs Dograh: Choosing an Open-Source Voice Agent Stack for In-House Teams
LiveKit vs Pipecat vs Dograh compared by layer: licenses, maintainers, release churn, cost per minute, migration paths and one test harness for all three.
Answering Machine Detection for Outbound Voice Agents in LiveKit and Pipecat (and How to Measure It)
How AMD works in LiveKit, Pipecat and Twilio, what each error costs per 10k dials, how to time voicemail drops, and how to measure false hang-ups.