Transport for the local turn-detector-v1-mini model.
The native model runs in the shared InferenceProcExecutor (one load per
host, ~138 MB) rather than in every job worker. Audio is buffered locally
in the job process (no per-frame IPC); on each inference window the last
~1.2 s is snapshotted, base64-encoded, and sent over IPC to the runner
(inference/eot/runner.ts) via executor.doInference(...).
When no executor is available (binding couldn't load on this platform),
predictions resolve to a positive default (1.0) so the session still
commits turns after minDelay — same as the existing local-failure path.
Transport for the local
turn-detector-v1-minimodel.The native model runs in the shared
InferenceProcExecutor(one load per host, ~138 MB) rather than in every job worker. Audio is buffered locally in the job process (no per-frame IPC); on each inference window the last ~1.2 s is snapshotted, base64-encoded, and sent over IPC to the runner (inference/eot/runner.ts) viaexecutor.doInference(...).When no executor is available (binding couldn't load on this platform), predictions resolve to a positive default (1.0) so the session still commits turns after
minDelay— same as the existing local-failure path.