# VibeVoice Review

> VibeVoice review: The open long-form/multi-speaker specialist - MIT weights, but Microsoft pulled the TTS code from the repo in Sept 2025 and frames the models.

![VibeVoice logo](https://www.versusref.com/logos/vibevoice.png)

The open long-form/multi-speaker specialist - MIT weights, but Microsoft pulled the TTS code from the repo in Sept 2025 and frames the models as research-only.

Among the 46 text-to-speech tools we track, VibeVoice has the 38th-widest language coverage.

See pricing · Open source · facts verified Jul 20, 2026

## What we know about VibeVoice

This is our verified profile of VibeVoice, a text-to-speech apis platform - the open long-form/multi-speaker specialist - MIT weights, but Microsoft pulled the TTS code from the repo in Sept 2025 and frames the models as research-only. Every fact about VibeVoice below carries the source it came from and the day we checked it.

VibeVoice does not publish a public per-minute rate we have been able to verify, so the price figure here stays blank until we can confirm one. We would rather show nothing than a guessed number; if you have a current VibeVoice quote, it is the fastest way for us to close that gap.

On capabilities, VibeVoice covers streaming audio output and self-host / on-prem option. Each of those is verified against VibeVoice's own docs or dashboard, not marketing copy.

Among the 46 text-to-speech tools in our matrix, VibeVoice leads with the 38th-widest language coverage; the fact sheet below has the raw numbers behind that placement.

In total we track 9 verified facts for VibeVoice today, each linking the primary source it came from so you can check our work - and vendor claims we have not measured ourselves are labeled as such on the VibeVoice fact sheet below.

## Fact sheet

### Capabilities

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Streaming audio output | ✓  Yes | Jul 20 | [source](https://github.com/microsoft/VibeVoice) |
| Languages supported | 2 languages | Jul 20 | [source](https://huggingface.co/microsoft/VibeVoice-1.5B) |

### Compliance & trust

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Self-host / on-prem option | ✓  Yes | Jul 20 | [source](https://huggingface.co/microsoft/VibeVoice-1.5B) |
| Model weights license | MIT | Jul 20 | [source](https://huggingface.co/microsoft/VibeVoice-1.5B) |

### Build experience

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Official SDKs | PyTorch | Jul 20 | [source](https://github.com/microsoft/VibeVoice) |
| Max input per request | Up to 90 min audio | Jul 20 | [source](https://huggingface.co/microsoft/VibeVoice-1.5B) |

### Commercial

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Model size (parameters) | TTS-1.5B (~3B total incl. tokenizers/diffusion head) | Jul 20 | [source](https://huggingface.co/microsoft/VibeVoice-1.5B) |
| Project maintenance status | active | Jul 20 | [source](https://github.com/microsoft/VibeVoice) |
| GitHub stars | 50,200 stars | Jul 20 | [source](https://github.com/microsoft/VibeVoice) |

Source: https://www.versusref.com/tts/tools/vibevoice/