Name: Elsa (Frozen) Disney Infinity | AI RVC Model
Brand: Weights
Rating: 4.0 (12 reviews)

WebKit

Introducing the Elsa (Frozen) Disney Infinity | RVC 2 40K | Harvest 300 Epochs model provided by Weights. This high-quality AI voice model, equipped with advanced RVC (Retrieval-Based Voice Conversion) technology, primarily caters to recreating voiceovers and speech. Entirely derived from authentic Disney Infinity files, it features a 32Khz sample rate and a total length of 8 minutes and 49 seconds, providing a diverse range of breathy sounds, grunts, groans, and laughs that mimic the enchanting voice of Elsa from Disney's Frozen. This AI music model, trained with a harvest batch size of 4 over 300 epochs pre-training, has an impressive 40K sample rate assuring top-notch output for every use-case. Whether you want to create AI covers or convert text-to-speech using our Elsa RVC model, it's pivotal to de-reverb your input audio for the perfect output. Test our seamless and intuitive AI tools today and start producing your very own AI musical covers or innovative text-to-speech creations for free. Leveraging the precision of our Elsa RVC model will elevate your auditory content to a delightfully recognisable and engaging level like never before.

Dataset from Disney Infinity only. Includes breathy sounds, grunts, groan, and laughs. Mainly for talking or speech, singing might work depending on the input audio. Tip: De-reverb your audio first before inferencing. Dataset Info Disney Infinity Files - 32Khz Sample Rate - 8 Minutes and 49 Seconds Length Training Settings Harvest - 4 Batch Size - 300 Epochs - 40K Sample Rate - Titan Pretrain Model

Elsa (Frozen) Disney Infinity

Elsa (Frozen) Disney Infinity | RVC 2 40K | Harvest 300 Epochs

scr_films

If i goes you crazy would you come and save me I don’t know how long can go take in it take in it take in it slow

Norrie

Updated model as of 5\28\24. Improvement from the last model and the dataset are now merged with talking and singing. Tip: De-Reverb your audio first before inferencing. Dataset Info Songs and Dialogue from Frozen 2 and Olaf's Frozen Adventure - 40Khz Sample Rate - 6 Minutes Length Training Settings Mangio Crepe - 8 Batch Size - 1400 Epochs - 40K Sample Rate - Normal V2 Pretrain Model

Anna (Frozen)

Anna (Frozen) | RVC 2 40K | Mangio Crepe 1400 Epochs

Extracted library from Native Instruments Dataset Info 9 Minutes Length - 8 Velocity Steps Per Sample - 40Khz Audio - Hard Rock Library (Kick, Snare, Cymbals, Rides, and Toms Only) Training Settings RMVPE - 8 Batch Size - 300 Epochs - 40K Sample Rate - Normal V2 Pretrain Model

Studio Drummer (Drum Library)

Studio Drummer (Drum Library) | RVC 2 40K | RMVPE 300 Epochs

Updated model as of 3\3\24. Big improvement from the last model and the dataset are now merged with talking and singing. Tip: De-Reverb your audio first before inferencing. Dataset Info Songs and Dialogue from Frozen 2 and Olaf's Frozen Adventure - 40Khz Sample Rate - 6 Minutes Length Training Settings RMVPE - 10 Batch Size - 600 Epochs - 40K Sample Rate - Normal V2 Pretrain Model

Anna (Frozen) | RVC 2 40K | RMVPE 600 Epochs

Updated model as of 2/24/24. Highest quality and accurate voice model of Elsa, big improvement from the past 6 months. The dataset are now merge with talking ad singing. Don't forget to credit me when model is used hehe. Tip: De-Reverb your audio first before inferencing. Dataset Info Songs and Dialogue from Frozen 2 and Olaf's Frozen Adventure - 40Khz Sample Rate - 6 Minutes and 30 Seconds Length Training Settings Mangio Crepe - 8 Hop Length - 4 Batch Size - 200 Epochs - 40K Sample Rate - Normal V2 Pretrain Model

Elsa (Frozen)

Elsa (Frozen) | RVC 2 40K | Mangio Crepe 300 Epochs

Trained with 19 mins dataset from one of her podcast using rmvpe. Tip: Recommend to use 1 as index setting to make her sound natural. But when you're experiencing voice cracks, lower the index to 0.5 or 0.6. Another thing, match the pitch with the sample audios below for natural speech. Not recommended as a singing model. Dataset Info: Unprocessed (just cuts, no noise reductions) 32Khz Sample Rate 180 Hz Average Pitch Frequency Spoken Training Settings: RMVPE 4 Batch Size 600 Epochs 32K Sample Rate Normal V2 Pretrain Model

Elsa (Frozen) Disney Infinity

Description

Samples

Saiba Momoi (Blue Archive)

Adel imam (Egyptian Actor) عادل امام (ممثل مصري)

JP Furina / Focalors CV: Inori Minase (Genshin Impact)

Ariana Grande AI

Hu Tao JP (Genshin Impact)

JENNIE of BLACKPINK [Strong Ver.]

Saiba Momoi (Blue Archive) (VA: Tokui Sora)

Hatsune Miku

SpongeBob SquarePants (Talking And Singing)

Takanashi Hoshino (from Blue Archive)

Satoru Gojo (JJK) [VA Yuichi Nakamura]

ENHYPEN Heeseung

Sunaokami Shiroko (Blue Archive)

Goku (Mario Castañeda) (Latin American Spanish) (UPDATE)

Villager (Minecraft)

Mortis [Brawl stars]

Jungkook (BTS)

Melodie - (Brawl Stars) - (English & Korean Voices)

Tendou Arisu (Blue Archive)

Kanye West