feat(tts): add female voice candidates (XTTS v2) + emotion tone samples
- samples/voice/: 6 XTTS v2 female studio voices speaking the same Korean line, as clearer-pronunciation alternatives to the single MeloTTS speaker - samples/emotion/: per-[emotion] delivery clips from the current MeloTTS engine - samples/README.md documents both sets and the tradeoffs Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
32
samples/README.md
Normal file
32
samples/README.md
Normal file
@@ -0,0 +1,32 @@
|
||||
# 음성 샘플 (voice / emotion samples)
|
||||
|
||||
브라우저나 로컬에서 들어보며 목소리·감정 톤을 고르기 위한 오디오 샘플 모음이다.
|
||||
Discord로 올리는 대신 여기에 보관한다.
|
||||
|
||||
## voice/ — 다른 여자 목소리 후보 (XTTS v2)
|
||||
|
||||
현재 라이브 TTS(MeloTTS 한국어)는 화자가 하나뿐이라 "다른 여자 목소리"를 낼 수 없다.
|
||||
대안으로 XTTS v2의 내장 여성 스튜디오 보이스로 같은 한국어 문장을 합성한 후보들이다.
|
||||
문장은 모두 동일하다: "안녕하세요, 저는 새로운 목소리예요. 한국어 발음이 또렷하게
|
||||
들리는지 한번 들어봐 주세요."
|
||||
|
||||
| 파일 | 화자 |
|
||||
|------|------|
|
||||
| xtts_01_ana_florence.mp3 | Ana Florence |
|
||||
| xtts_02_daisy_studious.mp3 | Daisy Studious |
|
||||
| xtts_03_sofia_hellen.mp3 | Sofia Hellen |
|
||||
| xtts_04_alexandra_hisakawa.mp3 | Alexandra Hisakawa |
|
||||
| xtts_05_nova_hogarth.mp3 | Nova Hogarth |
|
||||
| xtts_06_rosemary_okafor.mp3 | Rosemary Okafor |
|
||||
|
||||
트레이드오프: XTTS는 MeloTTS보다 발음이 또렷하고 자연스러운 여성 음색을 고를 수 있지만,
|
||||
합성이 더 무겁다(실시간 1초 예산과 충돌 가능). 라이브 채택 시 GPU 스트리밍으로 첫 소리
|
||||
지연을 실측해 맞춰야 한다. 생성 스크립트: `/home/claude/jarvis-tts/gen_xtts_voices.py`.
|
||||
|
||||
## emotion/ — 감정별 톤 샘플 (현재 라이브 MeloTTS)
|
||||
|
||||
현재 엔진(MeloTTS 한국어)의 `[감정]` 태그별 델리버리를 하나씩 들어보는 샘플이다.
|
||||
각 클립은 감정 이름을 기본 속도로 말한 뒤 그 감정 톤으로 예시 문장을 말한다.
|
||||
감정 구분은 피치가 아니라 말 빠르기로만 표현된다(피치 변조는 잡음 때문에 비활성).
|
||||
파일명이 감정을 그대로 담는다(예: `emo_02_happy.mp3` = 기쁨). 생성 스크립트:
|
||||
`tests/gen_emotion_samples.py`.
|
||||
BIN
samples/emotion/emo_01_base.mp3
Normal file
BIN
samples/emotion/emo_01_base.mp3
Normal file
Binary file not shown.
BIN
samples/emotion/emo_02_happy.mp3
Normal file
BIN
samples/emotion/emo_02_happy.mp3
Normal file
Binary file not shown.
BIN
samples/emotion/emo_03_excited.mp3
Normal file
BIN
samples/emotion/emo_03_excited.mp3
Normal file
Binary file not shown.
BIN
samples/emotion/emo_04_hopeful.mp3
Normal file
BIN
samples/emotion/emo_04_hopeful.mp3
Normal file
Binary file not shown.
BIN
samples/emotion/emo_05_sad.mp3
Normal file
BIN
samples/emotion/emo_05_sad.mp3
Normal file
Binary file not shown.
BIN
samples/emotion/emo_06_angry.mp3
Normal file
BIN
samples/emotion/emo_06_angry.mp3
Normal file
Binary file not shown.
BIN
samples/emotion/emo_07_fearful.mp3
Normal file
BIN
samples/emotion/emo_07_fearful.mp3
Normal file
Binary file not shown.
BIN
samples/emotion/emo_08_surprised.mp3
Normal file
BIN
samples/emotion/emo_08_surprised.mp3
Normal file
Binary file not shown.
BIN
samples/emotion/emo_09_disgust.mp3
Normal file
BIN
samples/emotion/emo_09_disgust.mp3
Normal file
Binary file not shown.
BIN
samples/emotion/emo_10_calm.mp3
Normal file
BIN
samples/emotion/emo_10_calm.mp3
Normal file
Binary file not shown.
BIN
samples/emotion/emo_11_friendly.mp3
Normal file
BIN
samples/emotion/emo_11_friendly.mp3
Normal file
Binary file not shown.
BIN
samples/emotion/emo_12_serious.mp3
Normal file
BIN
samples/emotion/emo_12_serious.mp3
Normal file
Binary file not shown.
BIN
samples/emotion/emo_13_disappointed.mp3
Normal file
BIN
samples/emotion/emo_13_disappointed.mp3
Normal file
Binary file not shown.
BIN
samples/emotion/emo_14_tired.mp3
Normal file
BIN
samples/emotion/emo_14_tired.mp3
Normal file
Binary file not shown.
BIN
samples/emotion/emo_15_affectionate.mp3
Normal file
BIN
samples/emotion/emo_15_affectionate.mp3
Normal file
Binary file not shown.
BIN
samples/emotion/emo_16_playful.mp3
Normal file
BIN
samples/emotion/emo_16_playful.mp3
Normal file
Binary file not shown.
BIN
samples/emotion/emo_17_curious.mp3
Normal file
BIN
samples/emotion/emo_17_curious.mp3
Normal file
Binary file not shown.
BIN
samples/emotion/emo_18_whisper.mp3
Normal file
BIN
samples/emotion/emo_18_whisper.mp3
Normal file
Binary file not shown.
BIN
samples/emotion/emo_19_shout.mp3
Normal file
BIN
samples/emotion/emo_19_shout.mp3
Normal file
Binary file not shown.
BIN
samples/emotion/emo_20_determined.mp3
Normal file
BIN
samples/emotion/emo_20_determined.mp3
Normal file
Binary file not shown.
BIN
samples/emotion/emo_21_relieved.mp3
Normal file
BIN
samples/emotion/emo_21_relieved.mp3
Normal file
Binary file not shown.
BIN
samples/voice/xtts_01_ana_florence.mp3
Normal file
BIN
samples/voice/xtts_01_ana_florence.mp3
Normal file
Binary file not shown.
BIN
samples/voice/xtts_02_daisy_studious.mp3
Normal file
BIN
samples/voice/xtts_02_daisy_studious.mp3
Normal file
Binary file not shown.
BIN
samples/voice/xtts_03_sofia_hellen.mp3
Normal file
BIN
samples/voice/xtts_03_sofia_hellen.mp3
Normal file
Binary file not shown.
BIN
samples/voice/xtts_04_alexandra_hisakawa.mp3
Normal file
BIN
samples/voice/xtts_04_alexandra_hisakawa.mp3
Normal file
Binary file not shown.
BIN
samples/voice/xtts_05_nova_hogarth.mp3
Normal file
BIN
samples/voice/xtts_05_nova_hogarth.mp3
Normal file
Binary file not shown.
BIN
samples/voice/xtts_06_rosemary_okafor.mp3
Normal file
BIN
samples/voice/xtts_06_rosemary_okafor.mp3
Normal file
Binary file not shown.
Reference in New Issue
Block a user