Warm synthesis mean — C013

Voice candidates were scored blind by embedding similarity and intelligibility, then chosen by listening — samples are not published.

Single reading

1.31 seconds

MEASURED recorded 13 September 2026

Protocol

Test definition

Offline ECAPA-TDNN speaker-embedding cosine to a fixed TEST-only reference centroid and Whisper round-trip WER over eight fixed original sentences unless stated. C008 control 0.916 s; first audio/streaming NOT measured.

Limits

Limitations

  • MEASURED_UNQUALIFIED. Similarity is diagnostic, not identity or quality; scores are only comparable within one reference population. Owner preference did not track similarity. DO NOT publish audio (rights flag in voice.md).

Log

Recorded values

Date Value Evidence Samples Source
13 September 2026 1.31 seconds MEASURED 8

Source paths refer to the private JARVIS repository and runtime records. They are listed for audit and are not published.