VibeVoice

Neural TTS model by Microsoft with expressive speech synthesis.

Open SourceSelf HostedOffline CapableGPU Required (6GB+ VRAM)
0.0 (0)

About

VibeVoice by Microsoft Research is a neural text-to-speech model aimed at expressive, natural synthesis with controllable prosody and emotion. The project later added VibeVoice-ASR, a unified speech-to-text model available through the Hugging Face Transformers library. Inference runs on a GPU and demo notebooks are provided. Released under the MIT license with model collections published on Hugging Face.

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
6 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)

Open-source dialogue TTS model by Nari Labs supporting multi-speaker conversations.

Open SourceSelf HostedOfflineGPU 6GB+
Easy
0.0 (0)

Pure language modeling approach to TTS without traditional audio codecs.

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)

Multilingual TTS with zero-shot voice cloning and streaming support.

Open SourceSelf HostedOfflineGPU 4GB+
Intermediate
0.0 (0)

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

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