VoiceCraft

Zero-shot speech editing and TTS using neural codec language models.

Open SourceSelf HostedOffline CapableGPU Required (8GB+ VRAM)
0.0 (0)

About

VoiceCraft from UT Austin is a token-infilling neural codec language model that performs both speech editing and zero-shot text-to-speech on in-the-wild audio such as audiobooks, podcasts, and videos. It can edit existing recordings or clone an unseen voice from a few seconds of reference, and ships code and demos. Inference uses a GPU with around 8 GB of VRAM. Distributed as open-source research.

Reviews (0)

Leave a Review

No reviews yet. Be the first to review!

Details

Price
Free
Platform
Local/Desktop
Difficulty
Advanced (4/5)
Minimum VRAM
8 GB
Added
Apr 3, 2026

Related Tools

Featured

Lightweight and expressive TTS model with 82M parameters for fast local inference.

Open SourceSelf HostedOffline
Easy
4.0 (1)

Conversational TTS model optimized for dialogue and chat applications.

Open SourceSelf HostedOfflineGPU 4GB+
Intermediate
0.0 (0)

Multilingual large voice generation model with full-stack inference, training, and deployment.

Open SourceSelf HostedOfflineGPU
Intermediate
0.0 (0)

Large-scale multilingual TTS model by Alibaba with zero-shot voice cloning.

Open SourceSelf HostedOfflineGPU 8GB+
Advanced
0.0 (0)

Emotion-controllable TTS engine by NetEase with 2000+ voices.

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

Transformer-based text-to-audio model by Suno that generates speech, music, and sound effects.

Open SourceSelf HostedOfflineGPU 4GB+
Intermediate
0.0 (0)
Browse all Text-to-Speech (TTS) tools