Evalgent

Blog

Page 56 of 59

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
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
Pipecat Interruption Strategy and Smart Turn v3: Settings That Work on Phone Audio
Voice AI Testing
22 min read

Pipecat Interruption Strategy and Smart Turn v3: Settings That Work on Phone Audio

Configure Pipecat interruption strategies, Smart Turn v3, Silero VAD and idle timeouts for 8 kHz phone calls, with latency math and a test plan.

October 4, 2026Read more
Pipecat Twilio Integration (and Telnyx): Media Streams vs SIP, Audio Formats, and the Failures to Test
Voice AI Testing
25 min read

Pipecat Twilio Integration (and Telnyx): Media Streams vs SIP, Audio Formats, and the Failures to Test

Pipecat Twilio integration from the wire up: Media Streams vs SIP, Telnyx traps, 8 kHz resampling, clear and mark events, hang-ups, costs, test matrix.

October 4, 2026Read more
LiveKit + Twilio Outbound Calling: SIP Trunk Setup and What to Test Before Go-Live
Voice AI Testing
25 min read

LiveKit + Twilio Outbound Calling: SIP Trunk Setup and What to Test Before Go-Live

LiveKit Twilio outbound call setup, leg by leg: Elastic SIP termination, CreateSIPParticipant, SIP codes, AMD, end-call, cost math, and go-live tests.

October 4, 2026Read more
LiveKit vs Pipecat for Telephony: SIP, Phone Numbers, and Real Calls
Voice AI Evaluation
17 min read

LiveKit vs Pipecat for Telephony: SIP, Phone Numbers, and Real Calls

LiveKit vs Pipecat telephony, compared hands-on: SIP trunks, dispatch rules, Twilio media streams, Daily SIP, DTMF, transfers, voicemail, failure modes.

Updated October 4, 2026Read more
Pipecat voice agent testing guide: frames, VAD, Smart Turn, and evals (2026)
Testing Strategies
24 min read

Pipecat voice agent testing guide: frames, VAD, Smart Turn, and evals (2026)

How to test a Pipecat voice agent in 2026: unit-test frame processors, tune Silero VAD and Smart Turn, run Pipecat Evals, and catch context drift.

Updated October 4, 2026Read more