Back to models
OV
New speed model

Microsoft VibeVoice

VibeVoice TTS

Long-form multi-speaker synthesis

Windows only

Generation

Up to 90 min

Speakers

Up to 4

Platform

Windows only

OpenVox fit

Dialogue + long-form

Model overview

Built into OpenVox for private local voice generation.

Use in OpenVox

VibeVoice TTS is a long-form, multi-speaker text-to-speech model designed for stable conversational audio and extended scripted generation.

VibeVoice can synthesize long-form speech of up to 90 minutes in a single generation workflow.

It supports up to four distinct speakers for conversations, podcasts, scripts, and narrated dialogue.

In OpenVox, VibeVoice TTS is available on Windows only and runs locally after its model files are downloaded.

OpenVox does not provide celebrity voice models and does not permit cloning, impersonating, or commercially using any person's voice without proper rights or consent.

Open-source model: Microsoft VibeVoice

View on Hugging Face