Breeze TTS 2

Breeze TTS 2 is an open-weight text-to-speech model from BreezeBlue, released on 2026-08-25 with both checkpoint weights and PyTorch inference code on GitHub. It is built for real-time interaction and, at release, ranked first among open-weight systems on the Artificial Analysis TTS leaderboard while also beating several frontier proprietary systems. The single model speaks English and Chinese naturally, and it lets you shape a voice from a description or steer a cloned voice with plain language.

Key Features

• Reference-free voice design: Describe a voice in natural language and Breeze TTS 2 creates it with no reference audio at all.
• Reference-guided voice direction: Clone a voice from reference audio, then steer tone, emotion, pace, and delivery with a sentence.
• Voice clone with transcript: Pass reference audio plus its exact transcript to preserve timbre, rhythm, emotion, and style.
• Inline vocal events: Add events directly in the text, such as (laugh), (cough), (clears throat), and (sigh) in English, or [笑], [咳嗽], [清嗓子], [叹气] in Chinese.
• Ultra-low latency: Sub-40 ms time to first audio on the warmed-up fast path, and an RTF of 0.32 (roughly 3.1x real time) on an NVIDIA H100.
• GPU-efficient: Eager inference uses about 7.7 GiB of GPU memory; a 12 GB card is the minimum recommended for the eager path.

Use Cases

Who Should Use This Tool?

• Interactive voice products: Developers building assistants that need to respond without a noticeable delay.
• Game and film voice teams: Small teams that want controllable voices without hiring a voice studio.
• Localization specialists: Teams that need one model for both English and Chinese output.

Problems It Solves

1. Latency kills conversation: Sub-40 ms time to first audio makes turn-taking feel natural.
2. Cloning is brittle: Reference-guided direction lets you adjust a voice after cloning instead of re-recording.
3. Design without a sample: Voice design gives you a starting voice from a text description alone.

Pricing

Advantages & Unique Selling Points

• Ranks first among open-weight TTS on the Artificial Analysis leaderboard at release, ahead of several closed systems.
• Two control modes: Reference-free voice design and reference-guided voice direction, plus classic voice cloning.
• Genuinely bilingual: One model handles English and Chinese rather than splitting into two checkpoints.

Getting Started

1. Clone breezeblue-ai/breeze-tts.
2. Install the checkpoint from BreezeBlue/Breeze-TTS-2.
3. Use a CUDA GPU with at least 12 GB for the eager path, or 24 GB for the fast path.
4. Start with a text prompt and add inline vocal events in your language.

Frequently Asked Questions

Can I use it commercially?

The inference code is Apache 2.0, but the weights, derivatives, and self-hosted output are for research and non-commercial use only. Check the license before shipping a product.

Does it need a reference audio to create a voice?

No. Voice design works from a natural-language description; voice direction and cloning need reference audio with its transcript.

Which languages does it support?

English and Chinese with a single model.

Alternatives

• Google Gemini 3.1 Flash TTS: Commercial frontier TTS with broad language coverage.
• ElevenLabs Turbo v2.5: Proprietary voice cloning platform.
• Deepgram Nova 2: Speech-to-text, the input side of a voice pipeline.

Tips

1. Use the fast path when latency matters, but budget 24 GB of GPU memory.
2. Provide a transcript with your reference audio for cleaner cloning.
3. Keep inline vocal events subtle; too many can sound over-produced.

Conclusion

Breeze TTS 2 is an open-weight, low-latency, bilingual TTS model that puts frontier voice quality and controllability on your own GPU. Start at the GitHub repo, check the license for your use case, and prototype a real-time voice experience before committing to a commercial path.

Limitation: this page is not a substitute for vendor docs. Recheck https://breezeblue.ai/breeze-tts-2 before you depend on a SKU.