All models
long-form

VibeVoice

MIT; additional model-card restrictions

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.

Hear VibeVoice

VibeVoice · Default · Same three scripts across the directory.

Run it yourself

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

Commercial conditions: The model card adds prohibited scenarios and describes the release as research/development, warning against commercial deployment without further testing. Treat the MIT tag and model-card restrictions together; commercial deployment is not cleared by this review.

Code: MIT. Weights: MIT tag with additional model-card use restrictions. License sources checked 2026-09-20. Source 1Source 2Source 3

Before you choose: Compare the samples with your own use case. Check the linked documentation for code, weight, and voice license terms.

Details awaiting a fresh review. Hardware figures are estimates unless a benchmark is linked.

Compare with similar

Compare all →
XTTS v2Listen side-by-side →Fish Speech 1.5Listen side-by-side →CosyVoice 2Listen side-by-side →

Choose an alternative to hear both models together.

Voices

1 voice
Neutral
Defaultdefault
—

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.”

Run VibeVoice

pip install vibevoice

Sources & setup details

VibeVoice FAQ

Do I need a GPU to run VibeVoice?

The directory lists roughly 16 GB of VRAM as a historical estimate. Check the model documentation for your checkpoint and runtime.

Can VibeVoice clone voices?

Yes — VibeVoice supports voice cloning from reference audio.

What license is VibeVoice released under?

VibeVoice is released under the MIT; additional model-card restrictions 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?

OpenSpeech Cloud is accepting production-access interest for VibeVoice, but this model is not currently hosted in Cloud. Use the official repository for current deployment options.