GameCult/Weksa
Watch
9
0
Fork
You've already forked Weksa
 0
Code Issues Pull requests 2 Projects Releases Packages Wiki Activity Actions

Target formant synth parity first

Browse source
This commit is contained in:
Meta Vens 2026-05-19 15:16:01 +01:00
commit de34bcb887
4 changed files with 101 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

4
state/map.yaml
View file

@ -40,6 +40,8 @@ constraints:
- Realtime neural voice output may be used as perceptual style/prosody
reference data, but not as physical ground truth for AquaSynth vocal-tract
tuning.
- First speech-lowering parity should target a simple open formant synth such
as eSpeak NG before realtime neural voice references.
invariants:
- Ontology owns meaning.
@ -198,6 +200,8 @@ open_questions:
AquaSynth after dialogue text exists?
- What capture format should store realtime voice references, transcripts,
prompt provenance, and rating notes for Nibu tuning?
- What minimal vocal intent DSL fields are needed to drive eSpeak NG parity
fixtures before AquaSynth `PhoneticIntent` parity?
landed_baseline:
- Language-neutral state spine.