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
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 DO NOT publish audio (rights flag in voice.md).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.