Skip to main content

Troubleshooting

IsSTTReady() returns false / no transcripts​

  • Confirm a model is downloaded (Tools → Elys Listen → Download Whisper Models) and that STT Model Path in Project Settings → Elys Listen (STT) points to it.
  • Confirm STT Backend is set to Whisper (Local) and Enable STT is on.
  • STT is client-side only — it intentionally does nothing on a dedicated server.

No audio is captured​

  • Check OS microphone permissions for the editor / packaged game.
  • Ensure the AudioCapture engine plugin is enabled (Elys Listen depends on it).
  • If using push-to-talk, make sure SetPushToTalkActive(true) is being called.

Transcription is inaccurate or wrong language​

  • Use a larger model (small or medium).
  • Set Config.LanguageCode to match the spoken language.
  • Background noise hurts accuracy; raise MinConfidenceThreshold to drop low-quality results.

High latency / hitches​

  • Whisper is batch (not streaming); larger models cost more per utterance. Use base/small for responsiveness.
  • Inference runs off the game thread, but very large models still take time to load at startup — load once via the subsystem, not per-actor.

Packaged build can't find the model​

  • The model file under Content/ElysListen/Models/ must be packaged. Add that folder to Project Settings → Packaging → Additional Non-Asset Directories to Package (or ship the model alongside and set an absolute path at runtime).

Still stuck? Ask on the Discord or via FAB Q&A.