
TVPaint Animation
The digital solution for your professional 2D animation projects.

A Singing Voice Conversion (SVC) tool using SoftVC content encoder and VITS architecture.

SoftVC VITS Singing Voice Conversion (so-vits-svc) is an open-source project focused on converting singing voices using AI. It employs a SoftVC content encoder to extract speech features from source audio, feeding them directly into a VITS model, preserving pitch and intonations. Unlike traditional TTS, so-vits-svc excels in SVC tasks by replacing the vocoder with NSF HiFiGAN to minimize sound interruption. The architecture supports shallow diffusion models for enhanced sound quality, Whisper-PPG encoder support, and static/dynamic sound fusion. Users train models independently using datasets, requiring consideration of dataset authorization. This framework allows developers to enable characters to perform singing tasks, with focus on fictional characters. The system is designed to operate offline, ensuring no user data is collected.
SoftVC VITS Singing Voice Conversion (so-vits-svc) is an open-source project focused on converting singing voices using AI.
Explore all tools that specialize in voice cloning. This domain focus ensures SoftVC VITS Singing Voice Conversion delivers optimized results for this specific requirement.
Extracts speech features from source audio, preserving pitch and intonations.
Replaces the standard vocoder to prevent sound interruption during conversion.
Integrates a shallow diffusion model to refine sound quality.
Allows encoding using Whisper-PPG features for improved representation.
Enables combining static and dynamic sound elements for creating hybrid voices.
Feature input changed to the 12th Layer of Content Vec Transformer output.
Install Python 3.7 or higher.
Clone the so-vits-svc repository from GitHub.
Install the required Python packages using `pip install -r requirements.txt`.
Prepare your training dataset, ensuring proper authorization.
Configure the `config.json` file with your dataset and training parameters.
Preprocess the dataset using provided scripts like `preprocess_flist_config.py` and `preprocess_hubert_f0.py`.
Train the model using `train.py`.
Use `inference_main.py` for voice conversion.
All Set
Ready to go
Verified feedback from other users.
"Generally positive sentiment, praising the tool's ability to create realistic voice conversions, although some users report challenges with initial setup and dataset preparation."
Post questions, share tips, and help other users.

The digital solution for your professional 2D animation projects.

Empowering independent artists with digital music distribution, publishing administration, and promotional tools.

Convert creative micro-blogs into high-performance web presences using generative AI and Automattic's core infrastructure.

Fashion design technology software and machinery for apparel product development.

Instantly turns any text to natural sounding speech for listening online or generating downloadable audio.

Professional studio-quality AI headshot generator for individuals and teams.