For synthesia infrastructure and model engineering teams
Synthesia video-model run: input stall, worker failure or inference delay?
Align video-input progress with distributed-worker and host evidence. Compare a resolved incident without confusing footage preparation, model training and video-serving latency.
Free 30-day Team evaluation. No card or automatic subscription. Work email verification required.
Replay a resolved Synthesia workflow incident
Upload your log file. Review the selected evidence and masking, then run diagnosis. Keep the original log for any follow-up questions.
Before uploading, review cloud data handling and local options.
Upload your log file. Large files are processed in your browser. Only selected evidence is submitted when you run diagnosis.
Try Denpex for 30 days. FREE.
No credit card. No automatic subscription. See whether Denpex helps with an incident you already understand.
Start your free 30-day Team evaluation
Up to 50 diagnoses a day for 30 days. Verify your work email to activate an eligible company evaluation, then replay a resolved incident and compare the evidence and next steps with your team's confirmed cause.
What a useful evaluation should establish
Compare one incident your team has already resolved with the first failure, quoted evidence and remaining questions. Begin with this question: Did footage preparation finish before the trainer stalled? Only assign a process, device or recovery state when the submitted evidence establishes it.
Did footage preparation finish before the trainer stalled?
Evidence to compare: Approved input-shard progress, decoder exceptions and worker-step timestamps.
Video preprocessing can stop delivering work before a training process reports a late symptom. Compare that boundary without assuming storage is the confirmed cause.
Which training generation and GPU image were involved?
Evidence to compare: Actual GPU allocation, runtime image revision and first distributed exception.
The published H100 and B200 examples are different configurations. A remedy from one experiment is not automatically compatible with another device or framework image.
Was the interruption in training or production generation?
Evidence to compare: Training-job identifier or serving request, worker exit and retained service timeline.
A delayed customer video and an interrupted training job require different evidence. Separate those owners before proposing changes to production capacity or a recovery artifact.
Use Denpex alongside your existing telemetry tools to investigate submitted incident evidence. With monitoring configured on a supported plan, detected failures can trigger alerts and an automatic diagnosis from the captured evidence.
Inside Denpex
See the evidence, not just the claim
Follow the causal chain, inspect the quoted evidence and prepare the next handoff. These actual product captures use founder-account examples and the VS Code extension, with the source identified under each image. Open a capture to inspect it at full size.
Follow the failure through the cascade
Prepare the hardware escalation
Ask for the evidence that is missing
Keep the investigation in the editor
