Commit graph

5 commits

Author SHA1 Message Date
fox
f58da54fa3 Expand to all 40 test-clean voices with idempotent registry 2026-01-27 15:30:42 -05:00
fox
af5c81928d Regenerate voices with upstream-verified genders from SPEAKERS.TXT 2026-01-27 13:22:26 -05:00
c56b8cb24e Simplify Makefile to run locally, remove all remote SSH/rsync
Remove REMOTE_HOST, REMOTE_USER, REMOTE_PATH, vars.sh loading.
All docker commands use sudo locally. Tests hit localhost:8000.
Delete old non-gendered voice WAV files (alloy, echo, fable, etc).
2026-01-27 12:51:08 -05:00
ebfa0319d1 Replace voices with 21 distinct gendered speakers from LibriSpeech
11 female (aria, clara, elena, grace, hazel, iris, luna, maya, ruby, sage, sofia)
10 male (atlas, caleb, felix, hugo, jasper, kai, leo, marcus, owen, theo)
Each voice is a unique LibriSpeech test-clean speaker for voice cloning diversity.
2026-01-27 12:41:37 -05:00
5e5e7936f1 Add 20 cloned voice samples for Qwen3-TTS
LJ Speech samples (public domain) for voice cloning:
- Standard: alloy, echo, fable, onyx, nova, shimmer
- Extended: amber, breeze, coral, dawn, ember, frost,
            glow, haze, ivy, jade, kite, lark, mist, nectar
2026-01-26 17:44:03 -05:00