# Breeze-TTS-2 Brings Open Voice Cloning to English

> BreezeBlue's second-generation text-to-speech model pairs voice cloning with controllable direction, all under an open release on Hugging Face.

Published by The Open Weights on Aug 25, 2026. Canonical: https://theopenweights.com/news/breeze-tts-2-dicn

## Key facts

- Company: BreezeBlue
- Model: Breeze-TTS-2
- Version: 2
- Category: Text → Speech
- Modalities: Text → Speech
- License: Other (Open weights, commercial use allowed)
- Architecture: BreezeForConditionalGeneration
- Precision: BF16
- Weights size: 7 GB
- Languages: English
- Significance: minor
- Published: 2026-08-25
- Last verified: 2026-09-14
- Hugging Face: https://huggingface.co/BreezeBlue/Breeze-TTS-2
- Canonical URL: https://theopenweights.com/news/breeze-tts-2-dicn

BreezeBlue has released [Breeze-TTS-2](https://huggingface.co/BreezeBlue/Breeze-TTS-2), an open text-to-speech model focused on English speech synthesis with voice cloning and controllable direction. The model is available now on Hugging Face under a custom license.

The headline feature is voice cloning, which lets users reproduce a target voice from reference audio rather than relying on a fixed set of built-in speakers. The model also emphasizes design and direction — a nod toward giving developers more control over how generated speech sounds, not just what it says.

## Why it matters

Open TTS models remain relatively scarce compared to the flood of open text and image models, and controllable voice cloning is usually locked behind commercial APIs. A freely available option lowers the barrier for developers building assistants, accessibility tools, and media applications who want to run synthesis locally.

A few details are worth noting for anyone evaluating it:

- English is the sole supported language at launch
- The model ships under an "other" custom license, so terms should be reviewed before commercial use
- Parameter count and audio sample rate are not specified in the release

As a second-generation model, Breeze-TTS-2 signals ongoing investment in the family, though BreezeBlue keeps a low profile. Interested developers can find weights and documentation on the project's [Hugging Face page](https://huggingface.co/BreezeBlue/Breeze-TTS-2).

## Get the model

- [Hugging Face](https://huggingface.co/BreezeBlue/Breeze-TTS-2)

## Sources

- [BreezeBlue/Breeze-TTS-2](https://huggingface.co/BreezeBlue/Breeze-TTS-2) — Hugging Face, Aug 25, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Breeze-TTS-2 Brings Open Voice Cloning to English", The Open Weights, Aug 25, 2026, https://theopenweights.com/news/breeze-tts-2-dicn