You're looking at a specific version of this model. Jump to the model overview.
zsxkib /hololive-style-bert-vits2:595ac420
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| speaker |
string
(enum)
|
EN_MoriCalliope
Options: EN_MoriCalliope, EN_TakanashiKiara, EN_NinomaeInanis, EN_GawrGura, EN_AmeliaWatson, EN_IRyS, EN_TsukumoSana, EN_CeresFauna, EN_OuroKronii, EN_NanashiMumei, EN_HakosBaelz, EN_ShioriNovella, EN_KosekiBijou, EN_NerissaRavencroft, EN_AiraniIofifteen, EN_KureijiOllie, EN_AnyaMelfissa, EN_VestiaZeta, JP_TokinoSora, JP_HoshimachiSuisei, JP_AZKi, JP_YozoraMel, JP_NatsuiroMatsuri, JP_AkiRosenthal, JP_AkaiHaato, JP_MinatoAqua, JP_NakiriAyame, JP_NekomataOkayu, JP_ShiranuiFlare, JP_ShiroganeNoel, JP_HoushouMarine, JP_TokoyamiTowa, JP_YukihanaLamy, JP_LaplusDarknesss, JP_TakaneLui, JP_HakuiKoyori, JP_SakamataChloe, JP_IchijouRirika |
Default speaker
|
| text_input |
string
|
Hello there! This is test audio of a new Hololive text to speech tool running on Replicate!
|
Text to convert to speech (text-to-voice)
|
| reference_audio_path |
string
|
Path to a reference audio file (voice-to-voice)
|
|
| line_split |
boolean
|
True
|
Whether to split the text into lines for processing
|
| split_interval |
number
|
0.5
|
Interval between splits when line_split is True
|
| style |
string
(enum)
|
Neutral
Options: Neutral, Normal, Excited, Sana, Baelz1, Baelz2, BaelzShouting, Anya, IofiLoud, Iofi, ZetaSoft, Zeta, ZetaLoud, Ollie, Koyori, Chloe, Lamy, Aqua, Sora, Towa, Suisei, Ayame, Haato, Matsuri, Mel, Aki, Lui, AZKi, Flare, Ririka, Laplus, Noel, Okayu, Marine, Kronii, NerissaLaugh, Calli, Nerissa, Japanese, Happy, Reading, Fauna, Amelia, MumeiLaugh, Shiori, IRyS, Ina, Gura, Mumei, ShioriLaugh, Scared, Angry |
Style of speech to use (choices may be limited based on the selected speaker)
|
| style_weight |
number
|
5
|
Weight of the style effect
|
| use_tone |
boolean
|
False
|
Whether to use tone information in the synthesis (Japanese only)
|
| sdp_ratio |
number
|
0.2
|
Ratio for speaker-dependent processing
|
| noise_scale |
number
|
0.6
|
Scale of noise to add to the synthesis
|
| noise_scale_w |
number
|
0.8
|
Scale of noise for the waveform
|
| length_scale |
number
|
1
|
Scale of the length of the synthesized speech
|
| style_text_weight |
number
|
0.7
|
Weight of the style text effect
|
| use_style_text |
boolean
|
False
|
Whether to use additional style text in the synthesis
|
| style_text |
string
|
|
Additional text to guide the style of the synthesis
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'format': 'uri', 'title': 'Output', 'type': 'string'}