Hugging Face's logo

dkounadis
/
artificial-styletts2

Text-to-Audio
Audiocraft
English
audiogen
styletts2
shift-tts
sound
audio-generation
text-to-speech
mimic3
Model card Files Community
4

Voices

#1
by dkounadis - opened
Discussion
dkounadis
 Owner
•
edited 23 days ago

Native Voices

Voice TTS Soundscape
0 en_UK_apope eagles
11 en_US_cmu_arctic_jmk sitar musre
14 en_US_cmu_arctic_lnh breezy humms
15 en_US_cmu_arctic_rxr lullaby wind
16 en_US_cmu_arctic_slp happy chirps
17 en_US_cmu_arctic_slt soft whirrr
18 en_US_hifi-tts_6097 cats meowin
20 en_US_hifi-tts_92
22 en_US_m-ailabs_elliot_miller rain fores
23 en_US_m-ailabs_judy_bieber shore of waves clasinhn at the shore
24 en_US_m-ailabs_mary_ann The image you provided appears to be a painting depicting a waterfront scene with sail and a dock. The style seems to reflect impressionistic brushwork, where the artist uses loose, visible strokes to capture the light and movement of the water and boats.
25 en_US_vctk_p225 elephants holwin
27 en_US_vctk_p227 harp musi
28 en_US_vctk_p228 sitar musre
34 en_US_vctk_p234 restauran garen
35 en_US_vctk_p236 train whisle
36 en_US_vctk_p237 train seulching at the slope on ucrce
39 en_US_vctk_p240 rivers n watefall
40 en_US_vctk_p241 guitar solo
41 en_US_vctk_p243 acoustic guitar
42 en_US_vctk_p244 harp music
43 en_US_vctk_p245 harp solo
44 en_US_vctk_p246 eold howl
45 en_US_vctk_p247 dragons fl
46 en_US_vctk_p248 dragon fl
47 en_US_vctk_p249 dragonw fl
48 en_US_vctk_p250 homming bird
49 en_US_vctk_p251 monster truck
54 en_US_vctk_p256 cymbals musi
55 en_US_vctk_p257 dogs bargr
56 en_US_vctk_p258 alley ship dogs barg
57 en_US_vctk_p259 sheeps
58 en_US_vctk_p260 sheeps howl
59 en_US_vctk_p261 A duck quacking as birds chirp and a pigeon cooing
60 en_US_vctk_p262 Railroad crossing signal followed by a train passing and blowing horn
62 en_US_vctk_p264 hammer
63 en_US_vctk_p265 blacksmith noises
64 en_US_vctk_p266 Arriving at the valley on galloping horses
65 en_US_vctk_p267 accordion music
66 en_US_vctk_p268 guitar music
68 en_US_vctk_p270
69 en_US_vctk_p271 byrdee chirrp-singette
72 en_US_vctk_p274 statue in shire, hill river, vogels.
73 en_US_vctk_p275 Tavern and shrine and people talking glass plates drink
74 en_US_vctk_p276 leeavs russtlyng-whispr
75 en_US_vctk_p277 distanteh byllez tynkl
76 en_US_vctk_p278 hap-peee kriket soongz
77 en_US_vctk_p279 syn-gingg byrddz chanter
80 en_US_vctk_p282 austrian musi
81 en_US_vctk_p283 dar trance
84 en_US_vctk_p286 scry cars rev
85 en_US_vctk_p287 guddeee vybez a-raund
87 en_US_vctk_p292 breezyee hummz a-gaen
88 en_US_vctk_p293 gentlyyee babble-bluub
89 en_US_vctk_p294 hap-peee chirps-ahoy
90 en_US_vctk_p295 gruff-ffe barrk-e-howl
91 en_US_vctk_p297 birds amazonia
92 en_US_vctk_p298 raain-a-lash-inggg smatt
93 en_US_vctk_p299 krack-klyngg brayk-a-boun
97 en_US_vctk_p303 wolff-howl-e-lamentt
98 en_US_vctk_p304 jett-enginn roarr i blaast
99 en_US_vctk_p305 trainn-whistle
100 en_US_vctk_p306
101 en_US_vctk_p307 watrr-fall-e-gurrgle
103 en_US_vctk_p310 Calm jazz melodes on a patio
107 en_US_vctk_p314 Classiccal orchestr
109 en_US_vctk_p317 Hard rock ruf open-
110 en_US_vctk_p318 acousti sess guitar
111 en_US_vctk_p323 Heavy metil thunder at a festival ground
112 en_US_vctk_p326 Ambient soundscapess in a botanical garden
113 en_US_vctk_p329 Salsa rythms at a street party
117 en_US_vctk_p335 Progressive house musc at a beach club
118 en_US_vctk_p336 Spiritual lullabi
119 en_US_vctk_p339 Afrobeat jams in a community park
120 en_US_vctk_p340 Gospel choirus outdoors
121 en_US_vctk_p341 Acoustic folk-popp at a vineyard
122 en_US_vctk_p343 Latin jazz flaver by the waterfront
123 en_US_vctk_p345 Industrial technoo in a warehouse district
124 en_US_vctk_p347 Blues rock licks on a porch
126 en_US_vctk_p360 New age melodeez in a desert landscape

Other voices Listen here

dkounadis changed discussion title from StyleTTS2 via Mimic-3 styles to StyleTTS2 - Mimic-3 styles
dkounadis changed discussion title from StyleTTS2 - Mimic-3 styles to StyleTTS2 - via - Mimic-3 Prompts
dkounadis changed discussion title from StyleTTS2 - via - Mimic-3 Prompts to StyleTTS2 - via - Mimic-3 Prompt
dkounadis changed discussion title from StyleTTS2 - via - Mimic-3 Prompt to StyleTTS2 - via - Mimic-3
dkounadis changed discussion title from StyleTTS2 - via - Mimic-3 to StyleTTS2 via Mimic-3
dkounadis changed discussion title from StyleTTS2 via Mimic-3 to StyleTTS2 - via - Mimic3 Stylisation
dkounadis changed discussion title from StyleTTS2 - via - Mimic3 Stylisation to StyleTTS2 - via - Mimic-3 Stylisation
dkounadis changed discussion title from StyleTTS2 - via - Mimic-3 Stylisation to DRAFT - StyleTTS2 - via - Mimic-3 Stylisation (Libri)
dkounadis changed discussion title from DRAFT - StyleTTS2 - via - Mimic-3 Stylisation (Libri) to DRAFT - StyleTTS2 - via - Mimic-3 Stylisation (LibriSpeech)
dkounadis changed discussion title from DRAFT - StyleTTS2 - via - Mimic-3 Stylisation (LibriSpeech) to DRAFT - StyleTTS2 - via - Mimic-3 Stylisation
dkounadis changed discussion title from DRAFT - StyleTTS2 - via - Mimic-3 Stylisation to DRAFT
dkounadis
 Owner
•
edited Sep 4, 2024

Please edit for MOS annotation

A

B

0

1

2

3

4

5

6

7

8

9

10

11
ZYJGO

4 4
1 4
5 5
5 4
3 4
1 4

hagenw
•
edited Sep 5, 2024

2 3
1 4
5 4
5 4
2 3
1 2

dkounadis
 Owner

A B

4* 5
3* 5
5 5
5 4
2 5
1 4

*ignoring the breath-noise between sentences

dkounadis changed discussion status to closed
dkounadis
 Owner
•
edited Jun 8

Foreign Voices

For now we use MMS TTS voices for non-english languages. Notice that we don't use prior means duration of official MMS TTS instead we opt for musicality pattern per language. Listen to non-English voices here.

dkounadis
 Owner
•
edited Jun 7

Audionar Timeline

We started from StyleTTS2 official English checkpoint and build SHIFT TTS w/o altering the inference implementation from StyleTTS2 only by designing various style vectors that sound cool. Today we built audionar for which we have deleted the diffusion process from StyleTTS2 and define a deterministic sinusoid phase for F0.

Now using the official StyleTTS2 checkpoint and voice we can compare SHIFT TTS vs Audionar

Official StyleTTS2 use

long form video StyleTTS2

audionar

long form video Audionar
dkounadis
 Owner
•
edited 29 days ago

Non Native English Voices

Those voices are produced by demo or live_demo.py. A voice is a style vector given to StyleTTS2. All voices below are artificial. Their style vectors have been produced by another TTS System - namely Mimic3.

Voice TTS Soundscape
0 af_ZA_google-nwu_0184 eagles
2 af_ZA_google-nwu_2418 spring thunder stro
3 af_ZA_google-nwu_6590 distnt bels
5 af_ZA_google-nwu_7214 whisprng wind
6 af_ZA_google-nwu_8148 lullabi
7 af_ZA_google-nwu_8924 drppng dew
10 bn_multi_00779 chirping crttrs
11 bn_multi_01232 breezy sways
12 bn_multi_01701 sparrow twittr
19 bn_multi_4046 dogs bargi
20 bn_multi_4811 rain forest
21 bn_multi_5958 cats mwo i rain fores
22 bn_multi_9169 rain fores
25 de_DE_m-ailabs_eva_k elephants holwin
27 de_DE_m-ailabs_ramona_deininger harp musi
28 de_DE_m-ailabs_rebecca_braunert_plunkett sitar musre
29 de_DE_thorsten-emotion_amused whistling with wind blowing
40 es_ES_m-ailabs_karen_savage guitar solo
41 es_ES_m-ailabs_tux acoustic guitar
42 es_ES_m-ailabs_victor_villarraza harp music
43 fa_haaniye harp solo
44 fi_FI_harri-tapani-ylilammi eold howl
45 fr_FR_m-ailabs_bernard dragons fl
47 fr_FR_m-ailabs_gilles_g_le_blanc dragonw fl
48 fr_FR_m-ailabs_nadine_eckert_boulet homming bird
52 gu_IN_cmu-indic_cmu_indic_guj_ad orchestrating
53 gu_IN_cmu-indic_cmu_indic_guj_dp hi hat musi
55 ha_NE_openbible dogs bargr
56 hu_HU_diana-majlinger alley ship dogs barg
87 it_IT_mls_8181 breezyee hummz a-gaen
96 it_IT_riccardo-fasol fiiree-roar-a-gnawl
100 jv_ID_google-gmu_01392 iyss-krack-a-shatttr
101 jv_ID_google-gmu_01519 watrr-fall-e-gurrgle
102 jv_ID_google-gmu_01932 nergetic
103 jv_ID_google-gmu_02059 Calm jazz melodes on a patio
104 jv_ID_google-gmu_02326 Uplifting0
105 jv_ID_google-gmu_02884 Driving techno traacks in a field
108 jv_ID_google-gmu_03424 Reggae groovs on a pier
109 jv_ID_google-gmu_03727 Hard rock ruf open-
110 jv_ID_google-gmu_04175 acousti sess guitar
111 jv_ID_google-gmu_04285 Heavy metil thunder at a festival ground
112 jv_ID_google-gmu_04588 Ambient soundscapess in a botanical garden
113 jv_ID_google-gmu_04679 Salsa rythms at a street party
114 jv_ID_google-gmu_04715 Operatic arias in an ampitheater
115 jv_ID_google-gmu_04982 Country musi
116 jv_ID_google-gmu_05219 Trap beats at a block party
117 jv_ID_google-gmu_05522 Progressive house musc at a beach club
118 jv_ID_google-gmu_05540 Spiritual lullabi
119 jv_ID_google-gmu_05667 Afrobeat jams in a community park
120 jv_ID_google-gmu_05970 Gospel choirus outdoors
122 jv_ID_google-gmu_06207 Latin jazz flaver by the waterfront
125 jv_ID_google-gmu_06941 Celtic musii outdoors
126 jv_ID_google-gmu_07335 New age melodeez in a desert landscape
127 jv_ID_google-gmu_07638 Bossa nova chill by a fountain
130 jv_ID_google-gmu_08002 Surf roock vibes by the ocean
131 jv_ID_google-gmu_08178 Electro-pop synnth at an outdoor stage
132 jv_ID_google-gmu_08305 Vibrant festivel beats under the sun
133 jv_ID_google-gmu_08736 Relaxing ambien sounds in a garden
134 jv_ID_google-gmu_09039 Energetic roock concert in a park
135 jv_ID_google-gmu_09724 Calm jazz melodes on a patio
136 ko_KO_kss Uplifting pop hyymns at a beach party
137 ne_NP_ne-google_0258 Mystical ethnic tunas in a forest
138 ne_NP_ne-google_0283 Smooth blues rhhthms
139 ne_NP_ne-google_0546 Acrotsuic guitar by a **vrier** (river), a gentle strum.
140 ne_NP_ne-google_0649 Birdsong melded with a **lute** (duel) flute's trill.
141 ne_NP_ne-google_0883 The **restf** (fester) ounds of wind chimes in the breeze.
142 ne_NP_ne-google_2027 An **earh** (hear) beat of drums mimicking the ocean's roar.
143 ne_NP_ne-google_2099 Opera sung under **statr** (start) skies, a celestial stage.
144 ne_NP_ne-google_2139 Electronic dance music in a **wofod** (wood) clearing.
145 ne_NP_ne-google_3154 A jazz **noote** (tone) drifting over a placid lake.
147 ne_NP_ne-google_3960 The **chorss** (cross) of a choir echoing through a canyon.
150 ne_NP_ne-google_6329 Classical strings in a **garnde** (garden), blooming melodies.
151 ne_NP_ne-google_6587 The **murd** (drum) circle in a forest, grounding energy.
152 ne_NP_ne-google_6834 Blues harmonica wailing like a **lonye** (lonely) wind.
153 ne_NP_ne-google_7957 A symphony evoking a **monst** (month) of changing seasons.
154 ne_NP_ne-google_9407 Chants resonating in a **veac** (cave), ancient echoes.
155 nl_bart-de-leeuw Pop music blasting by a **bcaeh** (beach) bonfire.
156 nl_flemishguy The **lyluba** (lullaby) of ocean waves with gentle guitar.
157 nl_nathalie Techno beats pulsaring through a **leifd** (field) at dawn.
158 nl_pmk World music played on a **hil** (hill), overlooking the valley.
159 nl_rdh The rhythmic chirping of crickets forming a natural percussion section.
160 pl_PL_m-ailabs_nina_brown A soaring eagle's cry woven into the melody of a dramatic orchestral piece.
166 te_IN_cmu-indic_kpn A wolf's mournful howl integrated into a haunting and evocative folk song.
172 tn_ZA_google-nwu_1483 A lion's majestic roar sampled and stretched into a deep, sustained synth pad.
173 tn_ZA_google-nwu_1498 The chattering of monkeys adding a chaotic yet energetic texture to a jungle theme.
174 tn_ZA_google-nwu_1932 The soft purr of a cat used as a warm, underlying drone in a cozy track.
175 tn_ZA_google-nwu_2839 The synchronized buzzing of cicadas creating a vast, shimmering atmospheric wash.
176 tn_ZA_google-nwu_3342 The elegant trumpeting of an elephant providing a grand, ceremonial fanfare.
177 tn_ZA_google-nwu_3629 The distinct call of a loon, adding a melancholic and wild element to a melody.
178 tn_ZA_google-nwu_4506 The gentle bleating of sheep used to create a soft, pastoral texture.
179 tn_ZA_google-nwu_4850 The sharp bark of a fox cutting through a quiet moment in a suspenseful score.
182 tn_ZA_google-nwu_6206 The squawking of parrots layered into a vibrant, tropical sound collage.
183 tn_ZA_google-nwu_6234 eagles
184 tn_ZA_google-nwu_6459 gentl breze summer brz
185 tn_ZA_google-nwu_7674 soft rainn
186 tn_ZA_google-nwu_7693 distnt bels
187 tn_ZA_google-nwu_7866 hapy criket
190 tn_ZA_google-nwu_8512 drppng dew
192 tn_ZA_google-nwu_8914 sumnr nites
dkounadis
 Owner
•
edited Jun 7

Phonetic Variation

Variation

YouTube

Official StyleTTS2 use

long form video StyleTTS2

audionar

long form video Audionar
dkounadis changed discussion title from DRAFT to Voices
dkounadis changed discussion status to open

Sign up or log in to comment