Evalgent

Blog

Page 27 of 52

LiveKit Noise Cancellation Self-Hosted: Krisp, BVC, AEC and How to Test Them
Voice AI Testing
23 min read

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.

October 4, 2026Read more
Measuring Pipecat Latency Stage by Stage: Metrics, Observers and the Numbers That Lie
Voice AI Testing
23 min read

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.

October 4, 2026Read more
Deepgram Flux vs Silero VAD vs a Turn-Detector Model: Which End of Turn Detection Voice Agent Method to Use
Voice AI Testing
23 min read

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.

October 4, 2026Read more
LiveKit Transfer Call and Pipecat Handoff Guide: Ending Calls, Warm vs Cold Transfer, SIP REFER vs Bridge
Voice AI Testing
23 min read

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.

October 4, 2026Read more
OpenAI Realtime API SIP vs a Media-Stream Bridge: Putting OpenAI Realtime, GPT-Live, or Gemini Live on a Phone Line
Voice AI Testing
24 min read

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.

October 4, 2026Read more
LiveKit vs Pipecat vs Dograh: Choosing an Open-Source Voice Agent Stack for In-House Teams
Voice AI Testing
24 min read

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.

October 4, 2026Read more
Answering Machine Detection for Outbound Voice Agents in LiveKit and Pipecat (and How to Measure It)
Voice AI Testing
25 min read

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.

October 4, 2026Read more
Pipecat Deployment in Production: A Self-Hosting Blueprint for Phone Agents
Voice AI Testing
25 min read

Pipecat Deployment in Production: A Self-Hosting Blueprint for Phone Agents

Pipecat deployment blueprint for phone agents: process model, Docker and Kubernetes setup, drain-safe deploys, capacity math, and Cloud vs self-host cost.

October 4, 2026Read more
Debugging a LiveKit Latency Issue End to End: Metrics, Waterfalls and Fixes
Voice AI Testing
23 min read

Debugging a LiveKit Latency Issue End to End: Metrics, Waterfalls and Fixes

Fix a LiveKit latency issue: map every metric to a hop, build p50/p95 waterfalls, find what e2e_latency misses, and apply the right fix per segment.

October 4, 2026Read more