All models
long-form

VibeVoice

MIT

Microsoft's long-form TTS — 90 minutes, 4 speakers

VibeVoice is Microsoft's long-form TTS: it can synthesize up to ~90 minutes of continuous audio with up to four distinct speakers in a single generation — built for podcast-style content. Ultra-low-frame-rate tokenizers keep generation efficient despite the scale.

Voices

1 voice
Neutral
Defaultdefault
—
NeutralEmotionalNumbers & Dates

The scripts

Neutral
“The quick brown fox jumps over the lazy dog near the riverbank.”
Emotional
“I can't believe you actually did it. This is incredible!”
Numbers & Dates
“On March 14th, 2025, the team raised $4.2 million at a 38% margin.”

Install

pip install vibevoice

VibeVoice FAQ

Do I need a GPU to run VibeVoice?

For practical speeds, yes — plan on roughly 16 GB of VRAM. If you'd rather not manage a GPU, hosted access to every model in this directory is coming via OpenSpeech Cloud.

Can VibeVoice clone voices?

Yes — VibeVoice supports voice cloning from reference audio.

What license is VibeVoice released under?

VibeVoice is released under the MIT license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does VibeVoice support?

VibeVoice supports English, Chinese, Spanish, French, German, Japanese, Korean.

Is there a hosted VibeVoice API?

Yes — OpenSpeech Cloud is launching hosted, pay-per-minute access to VibeVoice and every other model in this directory. No CUDA, Docker, or GPU needed.