Poppy (Talking Model)

Create

Poppy (Talking Model)

TTS / RealtimeRVC v2E-CelebEnglish
lmaodead user image
lmaodead
1 year ago
👀

616

👍

15

🪄

168

Description

Dataset is 18 minutes, but 10 of it is from the I'm Poppy video. Used Elevenlabs Nicole model. 100% stability and 50% clarity. Transposed up to +6. Side Note: Colab also keeps disconnecting every 5 minutes, so this took like 30 minutes just to infer two audio files. You might be able to get better examples than what is showcased here. Model

Comments

lmaodead user image
lmaodead
1 year ago

Showcase #1: Saying Hi

lmaodead user image
lmaodead
1 year ago

Showcase #2: Reading a bedtime story

x_14106 user image
x_14106
1 year ago

cant wait for era specific models lmao

juutetsu user image
juutetsu
1 year ago

Someone NEEDS to do a I Disagree model

x_14106 user image
x_14106
1 year ago

thats an album right? i didnt listen to anything post 2018 lol

juutetsu user image
juutetsu
1 year ago

You have to her popmetal era is amazing 😭

x_14106 user image
x_14106
1 year ago

i see i see

x_14106 user image
x_14106
1 year ago

i will look when i get home lol

lmaodead user image
lmaodead
1 year ago

Pls do. I would love to know how it turns out.

Lucifer Angel Satane Ghost user image
Lucifer Angel Satane Ghost
1 week ago

thank you

Add a comment

Samples

New
Classic
1. Singing
Male
English
2. Singing
Female
English
3. Singing (Dry)
Female
English
4. Singing (High)
Female
English
5. Singing 2
Male
English
6. Singing (Dry)
Male
English
7. Singing (Dry, High)
Male
English

Pitch

Selected Audio
Selected Audio