diff --git a/samples/README.md b/samples/README.md new file mode 100644 index 0000000..4d18164 --- /dev/null +++ b/samples/README.md @@ -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`. diff --git a/samples/emotion/emo_01_base.mp3 b/samples/emotion/emo_01_base.mp3 new file mode 100644 index 0000000..e834804 Binary files /dev/null and b/samples/emotion/emo_01_base.mp3 differ diff --git a/samples/emotion/emo_02_happy.mp3 b/samples/emotion/emo_02_happy.mp3 new file mode 100644 index 0000000..f37ca9c Binary files /dev/null and b/samples/emotion/emo_02_happy.mp3 differ diff --git a/samples/emotion/emo_03_excited.mp3 b/samples/emotion/emo_03_excited.mp3 new file mode 100644 index 0000000..fe02085 Binary files /dev/null and b/samples/emotion/emo_03_excited.mp3 differ diff --git a/samples/emotion/emo_04_hopeful.mp3 b/samples/emotion/emo_04_hopeful.mp3 new file mode 100644 index 0000000..81d3e28 Binary files /dev/null and b/samples/emotion/emo_04_hopeful.mp3 differ diff --git a/samples/emotion/emo_05_sad.mp3 b/samples/emotion/emo_05_sad.mp3 new file mode 100644 index 0000000..599eff9 Binary files /dev/null and b/samples/emotion/emo_05_sad.mp3 differ diff --git a/samples/emotion/emo_06_angry.mp3 b/samples/emotion/emo_06_angry.mp3 new file mode 100644 index 0000000..3500d74 Binary files /dev/null and b/samples/emotion/emo_06_angry.mp3 differ diff --git a/samples/emotion/emo_07_fearful.mp3 b/samples/emotion/emo_07_fearful.mp3 new file mode 100644 index 0000000..798efd2 Binary files /dev/null and b/samples/emotion/emo_07_fearful.mp3 differ diff --git a/samples/emotion/emo_08_surprised.mp3 b/samples/emotion/emo_08_surprised.mp3 new file mode 100644 index 0000000..6dd55be Binary files /dev/null and b/samples/emotion/emo_08_surprised.mp3 differ diff --git a/samples/emotion/emo_09_disgust.mp3 b/samples/emotion/emo_09_disgust.mp3 new file mode 100644 index 0000000..75acfce Binary files /dev/null and b/samples/emotion/emo_09_disgust.mp3 differ diff --git a/samples/emotion/emo_10_calm.mp3 b/samples/emotion/emo_10_calm.mp3 new file mode 100644 index 0000000..7e91cf4 Binary files /dev/null and b/samples/emotion/emo_10_calm.mp3 differ diff --git a/samples/emotion/emo_11_friendly.mp3 b/samples/emotion/emo_11_friendly.mp3 new file mode 100644 index 0000000..3151c7d Binary files /dev/null and b/samples/emotion/emo_11_friendly.mp3 differ diff --git a/samples/emotion/emo_12_serious.mp3 b/samples/emotion/emo_12_serious.mp3 new file mode 100644 index 0000000..34223b0 Binary files /dev/null and b/samples/emotion/emo_12_serious.mp3 differ diff --git a/samples/emotion/emo_13_disappointed.mp3 b/samples/emotion/emo_13_disappointed.mp3 new file mode 100644 index 0000000..fb9f3ea Binary files /dev/null and b/samples/emotion/emo_13_disappointed.mp3 differ diff --git a/samples/emotion/emo_14_tired.mp3 b/samples/emotion/emo_14_tired.mp3 new file mode 100644 index 0000000..132aaa1 Binary files /dev/null and b/samples/emotion/emo_14_tired.mp3 differ diff --git a/samples/emotion/emo_15_affectionate.mp3 b/samples/emotion/emo_15_affectionate.mp3 new file mode 100644 index 0000000..b033435 Binary files /dev/null and b/samples/emotion/emo_15_affectionate.mp3 differ diff --git a/samples/emotion/emo_16_playful.mp3 b/samples/emotion/emo_16_playful.mp3 new file mode 100644 index 0000000..ec15c36 Binary files /dev/null and b/samples/emotion/emo_16_playful.mp3 differ diff --git a/samples/emotion/emo_17_curious.mp3 b/samples/emotion/emo_17_curious.mp3 new file mode 100644 index 0000000..74663e7 Binary files /dev/null and b/samples/emotion/emo_17_curious.mp3 differ diff --git a/samples/emotion/emo_18_whisper.mp3 b/samples/emotion/emo_18_whisper.mp3 new file mode 100644 index 0000000..3bf7598 Binary files /dev/null and b/samples/emotion/emo_18_whisper.mp3 differ diff --git a/samples/emotion/emo_19_shout.mp3 b/samples/emotion/emo_19_shout.mp3 new file mode 100644 index 0000000..9698a8a Binary files /dev/null and b/samples/emotion/emo_19_shout.mp3 differ diff --git a/samples/emotion/emo_20_determined.mp3 b/samples/emotion/emo_20_determined.mp3 new file mode 100644 index 0000000..6f7dad8 Binary files /dev/null and b/samples/emotion/emo_20_determined.mp3 differ diff --git a/samples/emotion/emo_21_relieved.mp3 b/samples/emotion/emo_21_relieved.mp3 new file mode 100644 index 0000000..ac70eff Binary files /dev/null and b/samples/emotion/emo_21_relieved.mp3 differ diff --git a/samples/voice/xtts_01_ana_florence.mp3 b/samples/voice/xtts_01_ana_florence.mp3 new file mode 100644 index 0000000..af02499 Binary files /dev/null and b/samples/voice/xtts_01_ana_florence.mp3 differ diff --git a/samples/voice/xtts_02_daisy_studious.mp3 b/samples/voice/xtts_02_daisy_studious.mp3 new file mode 100644 index 0000000..57c9865 Binary files /dev/null and b/samples/voice/xtts_02_daisy_studious.mp3 differ diff --git a/samples/voice/xtts_03_sofia_hellen.mp3 b/samples/voice/xtts_03_sofia_hellen.mp3 new file mode 100644 index 0000000..9b13162 Binary files /dev/null and b/samples/voice/xtts_03_sofia_hellen.mp3 differ diff --git a/samples/voice/xtts_04_alexandra_hisakawa.mp3 b/samples/voice/xtts_04_alexandra_hisakawa.mp3 new file mode 100644 index 0000000..b629bf3 Binary files /dev/null and b/samples/voice/xtts_04_alexandra_hisakawa.mp3 differ diff --git a/samples/voice/xtts_05_nova_hogarth.mp3 b/samples/voice/xtts_05_nova_hogarth.mp3 new file mode 100644 index 0000000..55d6386 Binary files /dev/null and b/samples/voice/xtts_05_nova_hogarth.mp3 differ diff --git a/samples/voice/xtts_06_rosemary_okafor.mp3 b/samples/voice/xtts_06_rosemary_okafor.mp3 new file mode 100644 index 0000000..e9a7c3e Binary files /dev/null and b/samples/voice/xtts_06_rosemary_okafor.mp3 differ