FreeVC

Text-free one-shot voice conversion model requiring no text transcription.

Open SourceSelf HostedOffline CapableGPU Required (4GB+ VRAM)
0.0 (0)

About

FreeVC is a one-shot voice conversion model that changes a recording's voice to a target speaker without needing text transcription or alignment. It adopts the end-to-end VITS framework for waveform reconstruction and disentangles content from speaker identity using an information bottleneck on WavLM features with spectrogram-resize augmentation. It works from a single reference clip and is released under the MIT license.

Reviews (0)

Leave a Review

No reviews yet. Be the first to review!

Details

Price
Free
Platform
Local/Desktop
Difficulty
Intermediate (3/5)
License
MIT
Minimum VRAM
4 GB
Added
Apr 3, 2026

Related Tools

Zero-shot voice cloning mode of CosyVoice model by Alibaba.

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)

Community fork of RVC with additional features and optimizations.

Open SourceSelf HostedOfflineGPU 4GB+
Easy
0.0 (0)

Updated zero-shot voice cloning by MyShell with improved quality.

Open SourceSelf HostedOfflineGPU 4GB+
Easy
0.0 (0)
Featured

Voice cloning mode of XTTS-v2 for creating custom voice replicas.

Open SourceSelf HostedOfflineGPU 4GB+
Easy
0.0 (0)

Zero-shot voice cloning capabilities of Fish Speech model.

Open SourceSelf HostedOfflineGPU 6GB+
Easy
0.0 (0)
Featured

Easy-to-use voice conversion framework based on retrieval for real-time voice cloning.

Open SourceSelf HostedOfflineGPU 4GB+
Easy
0.0 (0)
Browse all Voice Cloning & Voice Conversion tools