Accept the BreezeBlue Research and Non-Commercial License to access these weights
These weights are a derivative of Breeze TTS 2 and remain governed by the BreezeBlue Research and Non-Commercial License Agreement. The complete, unmodified Agreement is the LICENSE file in this repository. Section 4(f) requires each recipient to accept it independently before accessing or using the weights, which is why this repository is gated. Approval is automatic once you accept. The full Agreement is reproduced at the bottom of the model card so that you can read it before deciding.
Read the Agreement before you accept. Gating means the LICENSE file in this repository is not readable until after you accept, so the complete text is reproduced in full at the bottom of the model card below, and the identical authoritative copy is publicly readable at https://huggingface.co/BreezeBlue/Breeze-TTS-2/blob/main/LICENSE (SHA-256 8b826c0957648ea1df2b870ba2627a93b502930c3ba40fa1af696cdfc2d2f0a3, byte-identical to the LICENSE shipped here). This is not an open source licence: it permits research and non-commercial use only, and any commercial use requires a separate written licence from BreezeBlue. Accepting shares your Hugging Face username and email address with the repository owner.
Log in or Sign Up to review the conditions and access this model content.
Vireo TTS 3B — MLX, bfloat16
An unofficial, unaffiliated Apple-silicon build derived from BreezeBlue/Breeze-TTS-2.
Derived from Breeze TTS 2 by BreezeBlue and licensed for research and non-commercial use only.
This repository is not produced, endorsed, sponsored or reviewed by BreezeBlue or RESONIA, INC. "Vireo" is this build's own name and carries no affiliation. The reference to Breeze TTS 2 is descriptive attribution required by Section 4 of the licence.
Breeze TTS 2 converted to MLX at unchanged numeric precision. No
quantization, no pruning, no training — every tensor stays bfloat16, the dtype
the upstream checkpoint ships. The audio codec is converted alongside it into an
MLX-native layout that decodes incrementally.
This is the quality reference, not the fast build. Its job is to show what the released checkpoint does on Apple silicon when nothing has been compressed, so that the cost of compressing it can be measured rather than assumed.
Which build should I use?
Probably not this one. On the machine both were measured on, this build runs at 0.41× real time and needs 7.0 GB of GPU memory. Use it when you want the unmodified numeric behaviour of the checkpoint, when you are measuring what compression costs, or when you are batching offline work and have memory to spare.
For anything interactive, use the mixed 4-bit build: 2.8× faster, 2.3× less memory, and it is the build that was actually optimized and evaluated end to end.
| This build | Optimized build | |
|---|---|---|
| Weights on disk | 5.9 GB | 2.1 GB |
| Peak GPU memory, single stream | 7.0 GB | 3.0 GB |
| Median real-time factor | 2.436 (0.41× real time) | 0.870 (1.15× real time) |
| Warm time to first audio, clone mode | 415-481 ms | 285-322 ms |
| Precision | bfloat16, unpruned | mixed int4/int8, pruned |
Neither build is a replacement for upstream's PyTorch/CUDA release on non-Apple hardware.
Usage
The MLX runtime ships in this repository, as the breeze_mlx/ package. It
is the same code every number on this page was measured with. You do not need a
separate checkout, and you do not need PyTorch to generate speech.
Install
pip install "mlx>=0.32" numpy soundfile transformers
hf download mchen04/Vireo-TTS-3B-MLX-bf16 --local-dir vireo # accepts the licence gate first
cd vireo && python -m breeze_mlx.cli . --text "Hello there." --output out.wav
That is the whole dependency list for text-to-speech. transformers is used
only to build the tokenizer from tokenizer.json; no model is loaded through it.
Verified environment
Everything on this page was produced on the machine described under Benchmarks. The clean-room check that runs the downloaded repository with no local checkout used:
python 3.12.13
mlx 0.32.2
numpy 2.5.2
soundfile 0.14.0
transformers 5.16.1 # tokenizer only; 4.57.3 also verified
The optimization work itself was done with transformers==4.57.3. Both major
versions are tested: the runtime builds the tokenizer directly from
tokenizer.json rather than through AutoTokenizer, because the automatic route
inspects config.json and transformers 5 rejects this model's config for reasons
unrelated to tokenizing. Both routes produce identical token ids.
Optional extras
| For | Install |
|---|---|
| Voice cloning from a reference clip | pip install torch torchaudio qwen-tts |
Streaming HTTP server (breeze_mlx.server) |
pip install fastapi uvicorn python-multipart |
Long-form narration (breeze_mlx.audiobook) |
ffmpeg and ffprobe on PATH |
Voice cloning also needs upstream's codec encoder weights, which a converted bundle does not carry — decoding is native MLX and never uses them, and they are 682 MB:
hf download BreezeBlue/Breeze-TTS-2 --include 'audio_tokenizer/*' --local-dir breeze-tts-2
export BREEZE_AUDIO_TOKENIZER=$PWD/breeze-tts-2/audio_tokenizer
Python
from breeze_mlx import BreezeMLXRuntime, GenerationConfig, MLXCodec
bundle = "vireo" # this repository, downloaded
codec = MLXCodec(bundle)
runtime = BreezeMLXRuntime(bundle, codec=codec,
generation=GenerationConfig(max_new_tokens=750))
request = {
"text": "The morning fog had not yet lifted from the harbour.",
"instruction": "A warm, thoughtful young woman with a clear voice.",
"speaker": "S0",
}
chunks = []
for chunk in runtime.stream(request, template="tts_instruction",
cfg_scale=1.0, seed=42):
if chunk.audio.size:
chunks.append(chunk.audio) # float32, 24 kHz mono, streamed
Voice cloning takes a reference clip and its exact transcript:
from breeze_mlx import encode_reference
codes = encode_reference("reference.wav") # needs the extras above
request |= {"ref_text": "exact transcript of reference.wav"}
for chunk in runtime.stream(request, template="ref_edit_tata",
cfg_scale=1.0, seed=42, audio_codes=codes):
...
Voice design without a reference clip uses template="tts_instruction" and
benefits from classifier-free guidance (cfg_scale=4.0), which runs a two-branch
batch and is measurably slower per second of audio.
Other entry points
python -m breeze_mlx.bench . # the benchmark on this page
python -m breeze_mlx.server . # streaming HTTP server
python -m breeze_mlx.audiobook --help # long-form narration
python -m breeze_mlx.build_final --help # rebuild the weights from source
File layout
| File | What it is |
|---|---|
weights.safetensors |
765 tensors, all bfloat16: the language stack (text_encoder.*, backbone.*, depth.*, lm_head.*, text_encoder_proj.*). No .scales or .biases — nothing is quantized. |
codec.safetensors |
253 tensors: the audio codec decoder in MLX layout |
mlx_meta.json |
source repo and revision; quantization.name is bf16 with every per-stage field null |
codec_meta.json |
codec geometry: 16 codebooks, 24 kHz, 1920 samples per frame, sliding window 72 |
config.json, generation_config.json |
byte-identical to upstream |
tokenizer.json, tokenizer_config.json, special_tokens_map.json |
byte-identical to upstream |
audio_tokenizer/*.json |
byte-identical to upstream |
LICENSE |
the complete BreezeBlue Agreement, byte-identical to upstream's |
NOTICE |
required attribution notice |
MODIFICATIONS.md |
every change made to the Model Materials |
breeze_mlx/ |
the MLX runtime: the package that loads and runs these weights (Apache-2.0) |
LICENSE.apache-2.0 |
the licence covering breeze_mlx/, which is not the licence covering the weights |
SHA256SUMS |
digest of every file in this repository |
Loading tokenizer.json with transformers prints a warning about a Mistral
regex pattern. It comes from the upstream tokenizer file, which is unmodified
here, and is cosmetic.
Model
| Stage | Type | Layers | Hidden | MLP width |
|---|---|---|---|---|
| Text encoder | t5gemma2_text |
26 | 1152 | 6912 |
| Backbone | qwen3 |
28 | 2048 | 6144 |
| Depth decoder | 16-codebook RVQ head | 12 | 1024 | 8192 |
| Codec | Mimi-style, 24 kHz | 8 | 512 | — |
2.92 B parameters in the language stack, 114 M in the codec. Every shape is upstream's; nothing here is narrowed.
Benchmarks
One machine. One voice. Read the caveats.
| Machine | MacBook Pro Mac14,7, Apple M2, 8 cores (4P/4E), 16 GB unified memory |
| OS | macOS 26.5.2 (build 25F84) |
| Stack | mlx==0.32.2, Python 3.12.13 |
| Method | fastest of 3 repeats per timing probe; the minimum is the least biased estimate of what the code can do, and therefore a best case, not an expectation |
| Reference clip | one 7.5 s English clip of a single adult female speaker, not distributed |
Single stream
Clone mode (ref_edit_tata, CFG 1.0) except the last row.
| Case | Audio | Generated in | Real-time factor | × real time | Time to first audio |
|---|---|---|---|---|---|
| Short (1 sentence) | 2.64 s | 6.67 s | 2.527 | 0.40× | 415 ms |
| Medium (2 sentences) | 6.96 s | 16.33 s | 2.346 | 0.43× | 420 ms |
| Long (4 sentences) | 18.16 s | 41.15 s | 2.266 | 0.44× | 481 ms |
| Voice design, CFG 4.0 | 7.04 s | 27.74 s | 3.940 | 0.25× | 403 ms |
Median real-time factor 2.436. This build does not reach real time in single- stream mode on this machine, in any measured case.
Verified from a clean machine
Both repositories are checked end to end after every upload, from a process with
no access to any source checkout: an empty Hugging Face cache, a fresh virtual
environment holding only mlx, numpy, soundfile and transformers, and
no PyTorch installed at all. The runtime imported is the breeze_mlx/ in the
downloaded repository — the check asserts that and fails if any other copy is
importable.
| this build | the other build | |
|---|---|---|
| Files hash-verified | 40 (24 of them runtime) | 40 (24 of them runtime) |
| Hash mismatches | 0 | 0 |
| Anonymous download | refused (GatedRepoError) |
refused (GatedRepoError) |
| Load | 3.08 s | 2.16 s |
| Audio produced | 7.84 s | 7.76 s |
| Generated in | 20.36 s | 6.59 s |
| Real-time factor | 2.597 | 0.849 |
| × real time | 0.385× | 1.177× |
| Time to first audio | 1114 ms | 389 ms |
| Peak GPU memory | 6515 MB | 2622 MB |
| Peak process RSS | 3212 MB | 2640 MB |
| Output | 188,160 samples, all finite | 186,240 samples, all finite |
| Output peak / RMS | 0.4324 / 0.0653 | 0.3127 / 0.0423 |
The generated WAV is byte-identical to the one produced from the local bundle before upload:
d80bf229c8f46a6120de692af31d67ce5a42f20568371f6c5b8f358faf5d7fe1 7.84 s of 24 kHz mono PCM-16
This is a voice-design prompt at CFG 1.0 with seed=42 and
max_new_tokens=750, so it is reproducible, but it is a single sample and not a
benchmark — the numbers under Benchmarks are the measured ones.
Startup and memory
| Load (weights + codec, cold process) | 5.92 s |
| Cold time to first audio, first generation of the process | 1292 ms |
| Warm time to first audio, clone mode | 415-481 ms |
| Warm time to first audio, best probe overall (voice design) | 403 ms |
| Peak GPU memory, single stream | 6965 MB |
On a 16 GB machine that is comfortable. On an 8 GB machine this build will not run.
Batch
Offline batched synthesis, one shared voice, no classifier-free guidance. Wall time includes codec decode. Fastest of 2 repeats.
| Batch | Audio produced | Wall time | × real time | Peak GPU memory |
|---|---|---|---|---|
| 1 | 5.52 s | 13.25 s | 0.42× | 8934 MB |
| 2 | 11.12 s | 26.70 s | 0.42× | 9383 MB |
| 4 | 20.96 s | 26.51 s | 0.79× | 10280 MB |
| 8 | 41.76 s | 30.53 s | 1.37× | 12074 MB |
This is the one place this build is genuinely interesting: batched, it crosses real time. Decode is bandwidth-bound and the bytes pulled per frame are the same whether one sequence or eight are in flight, so batching converts a bandwidth-bound loop into a compute-bound one. At batch 8 it needs 12.1 GB, which fits a 16 GB machine and does not fit a smaller one. All 8 sequences produced finite, non-empty audio and none hit the token limit.
The optimized build still wins on throughput at every batch size (1.91× at batch 8), and by a wide margin on memory.
Quality
Measured by the same sealed harness, at the same settings, as the optimized
build: 24 probes, three seeds each, transcribed with Whisper small.en, speaker
similarity by microsoft/wavlm-base-plus-sv x-vector cosine.
| This build (bfloat16) | Optimized build (mixed 4-bit) | |
|---|---|---|
| Word error rate (mean) | 0.0235 | 0.0093 |
| Word error rate (median) | 0.0000 | 0.0000 |
| Speaker similarity (mean) | 0.9598 | 0.9580 |
| Speaker similarity (min over probes) | 0.9031 | 0.8559 |
| Stability (probes that produced audio) | 1.00 | 1.00 |
| Defect score | 0.0002 | 0.0001 |
| Clipping / non-finite samples | 0 / 0 | 0 / 0 |
| Peak GPU memory (harness) | 6609 MB | 2807 MB |
Read this table carefully — the uncompressed build has the higher word error rate. That is a real measurement, repeated over three seeds, and it is not a mistake. Two things explain it, and neither says the compressed build is "better".
The 0.0093 figure is a selected number. The mixed 4-bit configuration is the survivor of more than sixty candidates, each scored on this probe set with this ASR, with word error rate acting as a gate. Selecting hard against a metric buys performance on it. When that build was finally run against held-out probes it scored 0.0368 — four times its development figure. This build was never tuned against the probe set at all, so its 0.0235 carries no such selection.
The floor moved the other way. This build's worst speaker similarity across all probes is 0.9031, against the optimized build's 0.8559. The compressed build's mean similarity is fractionally higher; its floor is meaningfully lower. If consistency across prompts matters more to you than the average, that difference points the other way from the word error rate.
Both builds produced audio on every probe, with no clipping, no non-finite samples and near-identical defect scores. The honest summary is that these two are close on quality and far apart on cost, and that the compressed build's development-set word error rate should not be read as a quality claim over this one.
What these numbers do not establish
- Speed does not transfer. Every figure comes from one M2 with 16 GB. The decode loop is memory-bandwidth-bound, so an M2 Pro, M3 or M4 will differ. No claim is made about any machine other than the one named above.
- The headline is a best case. Speed is the fastest of three repeats.
- Quality was measured, not judged. Word error rate, x-vector similarity, F0 statistics and artifact counters catch intelligibility loss, timbre drift, prosodic flattening and signal defects. A candidate could still sound worse in a way none of them registers. There is no listening test behind these numbers.
- Word error rate is instrument-relative. Whisper
small.en. A stronger ASR would give different absolute numbers. - Speaker similarity is one clip of one voice. It does not discriminate finely between similar-sounding speakers of the same demographic.
- One language was evaluated. English only, although the model supports Chinese.
- "Full quality" means unmodified weights, not best achievable audio. This build preserves the checkpoint's numerics; it does not tune sampling, prompting or the codec for maximum perceived quality.
- Sampling does not reproduce upstream's token sequences. MLX and PyTorch use different random number generators. Correctness was established by stagewise numeric parity and greedy-decode agreement, not by matching sampled output. If you need bit-exact agreement with the PyTorch runtime, this is not it.
Reproducing this build
python -m breeze_mlx.build \
--src <upstream checkpoint @ c1c8ca18b70b30822735633991d9ebf4898e47d4> \
--dst <output bundle> \
--preset bf16
Unlike the optimized build, this one is fully reproducible by anyone with the
upstream checkpoint. There is no calibration step, so there is no private input:
the conversion is a deterministic function of the source weights alone. Verify
with the SHA256SUMS in this repository.
Checksums
SHA256SUMS in this repository covers every file. The weights:
e097dea6aa69a14971e17386b54aefad85d20bff363843870bf50016239908c7 weights.safetensors
cea6c821f4a3a69fdddd6a0500ce1ace293041107219d3fa173badce91730889 codec.safetensors
codec.safetensors is byte-identical to the one in the optimized build — the
codec conversion is the same in both, and only the language stack differs.
Source checkpoint, verified against the Hub's published LFS digests before conversion:
abf813781256e10cbe81f2dbb415f897556225d4dfa0282d67aa8ea164e114a9 model-00001-of-00002.safetensors
36aa73b1a11361e1774db90d9c63c63303b294c022de112aa51904d940edcef1 model-00002-of-00002.safetensors
Related work
A bfloat16 MLX conversion of this model already exists. If you want one that loads with the community's existing Breeze tooling, it is the better choice — this repository ships its own runtime instead:
mlx-community/Breeze-TTS-2-mlx— bfloat16, in the sharded Hugging Face layout, shipping upstream's PyTorch audio tokenizermlx-community/Breeze-TTS-2-mlx-8bitmlx-community/Breeze-TTS-2-mlx-4bit
What is different here, stated plainly so you can decide it does not matter to
you: this build fuses the language stack into a single weights.safetensors in
an MLX module layout, and converts the codec to MLX as well (253 tensors,
incremental decode) rather than shipping the PyTorch audio tokenizer. That is
what makes the streaming path and the batch numbers above possible. It is a
packaging and runtime difference, not a better model — the weights are the same
numbers.
Its real purpose in this pair is to be the uncompressed control for the optimized build.
Licence, attribution and responsible use
Derived from Breeze TTS 2 by BreezeBlue and licensed for research and non-commercial use only.
Breeze TTS 2 is licensed under the BreezeBlue Research and Non-Commercial
License Agreement. Copyright (c) 2026 RESONIA, INC. All Rights Reserved.
The complete, unmodified Agreement is LICENSE in this repository,
byte-identical to the one upstream ships. It is not an open source licence.
Two licences, covering different things
| Licence | Applies to | |
|---|---|---|
| The weights | BreezeBlue Research and Non-Commercial (LICENSE) |
weights.safetensors, codec.safetensors, the tokenizer and the configs |
| The runtime | Apache-2.0 (LICENSE.apache-2.0) |
the breeze_mlx/ package |
This split is not an interpretation. Section 1.2 of the BreezeBlue Agreement
says Model Materials "do not include source code expressly licensed under the
Apache License, Version 2.0", and Section 14.2 says such source is governed by
its own licence. The code in breeze_mlx/ is therefore Apache-2.0 and carries
none of the non-commercial restriction.
That does not make the pair commercially usable. The runtime is a loader for weights that remain restricted, and running these weights for a Commercial Purpose is forbidden whatever the code licence says.
- Research and non-commercial use only. Commercial use of these weights, of anything derived from them, or of their output requires a separate written licence from BreezeBlue. There is no creator, monetization, small-business or revenue-threshold exception.
- Each recipient must accept the Agreement independently (Section 4(f)).
That is why this repository is gated. If you redistribute these weights you
must impose the same requirement, ship the complete Agreement and the
NOTICEfile, keep every attribution and copyright notice, state your own modifications, and licence your distribution under this same Agreement without adding conflicting terms. - Voice cloning consent. Section 5(c) forbids using this model to clone, simulate or imitate a real person's voice, identity or likeness without that person's explicit and legally sufficient consent, and Section 5(d) requires you to hold all rights to any reference audio you submit. Section 5(i) forbids distributing synthetic audio where a reasonable person would be materially misled about its origin.
- No endorsement. BreezeBlue and RESONIA, INC. have not reviewed, approved or endorsed this build. No trademark licence is granted beyond the descriptive attribution Section 4 requires.
- Warranty and liability. The Agreement disclaims all warranties and caps BreezeBlue's aggregate liability at US$100. Sections 9, 10 and 11 apply to you.
Commercial licensing: https://breezeblue.ai · contact@breeze.blue
Appendix: the complete licence text
Gating this repository has one awkward consequence — the LICENSE file inside it
is not readable until after you have accepted. Asking someone to agree to a
document they cannot open is not informed consent, so the complete Agreement is
reproduced here, in the model card, which renders publicly.
This text is byte-identical to the LICENSE file in this repository and to
upstream's own copy at
BreezeBlue/Breeze-TTS-2/LICENSE,
which is not gated and can be read there instead. All three have SHA-256
8b826c0957648ea1df2b870ba2627a93b502930c3ba40fa1af696cdfc2d2f0a3.
BreezeBlue Research and Non-Commercial License Agreement, Version 1.0 — full text
BREEZEBLUE RESEARCH AND NON-COMMERCIAL LICENSE AGREEMENT
Version 1.0
Last Updated: August 25, 2026
This BreezeBlue Research and Non-Commercial License Agreement (the
"Agreement") is entered into between RESONIA, INC., doing business as
BreezeBlue ("BreezeBlue," "Licensor," "we," or "us"), and the individual or
entity accessing, using, modifying, or distributing any Model Materials
("You," "Your," or "Licensee").
By accessing, downloading, using, modifying, or distributing any portion of
the Model Materials or a Derivative Model, You acknowledge that You have read,
understood, and agreed to this Agreement. If You act on behalf of an entity,
You represent that You have authority to bind that entity, and "You" includes
both You and that entity.
This Agreement permits research and non-commercial use of the Model Materials
free of charge. It does not grant any commercial rights and is not an open
source license. Commercial use requires a separate written license from
BreezeBlue.
1. DEFINITIONS
1.1 "Model" means the Breeze TTS 2 model.
1.2 "Model Materials" means the Model weights, checkpoints, parameters,
adapters, model-specific tokenizer or codec weights, embeddings, and other
machine-learning artifacts that BreezeBlue expressly makes available under
this Agreement, together with any accompanying documentation expressly
designated as part of the Model Materials.
Model Materials do not include source code expressly licensed under the
Apache License, Version 2.0, or any third-party component made available under
its own license.
1.3 "Derivative Model" means any modification, adaptation, fine-tune, LoRA,
merge, quantization, distillation, or other model that is based on or derived
from the Model Materials, including a model created using the weights,
parameters, activations, embeddings, or Outputs of the Model Materials to
replicate or materially transfer their speech or audio generation
capabilities. Outputs themselves are not Derivative Models.
1.4 "Output" means audio, speech, text, metadata, or other content generated
by the Model Materials or a Derivative Model in response to an input.
1.5 "Research Purpose" means academic or scientific research that is not
primarily intended for commercial advantage or monetary compensation,
including peer-reviewed research, reproducibility studies, benchmarking,
evaluation, security testing, and red-teaming.
1.6 "Non-Commercial Purpose" means personal, educational, hobbyist, or other
use that is not primarily intended for commercial advantage or monetary
compensation, including limited evaluation and testing.
1.7 "Commercial Purpose" means any use primarily intended for or directed
toward commercial advantage, business benefit, or monetary compensation,
whether direct or indirect. Commercial Purpose includes, without limitation:
(a) production use or use in a product, service, or business operation;
(b) hosting or making the Model Materials, a Derivative Model, or their
functionality available through an API, SaaS offering, application, plug-in,
website, or other service;
(c) creating or providing content, products, or services for a fee, for a
client, in connection with advertising, sponsorship, subscription revenue,
or any other monetized activity;
(d) using the Model Materials, a Derivative Model, or Outputs for an
organization's internal operations beyond limited evaluation; or
(e) distributing, licensing, selling, or otherwise commercializing the Model
Materials or a Derivative Model.
The status of a Licensee as a for-profit entity does not, by itself, make
limited internal research, benchmarking, evaluation, security testing, or
red-teaming a Commercial Purpose, provided that the use is not deployed in
production, made available to customers or other external end users, used to
generate revenue, or used to train or improve a non-BreezeBlue generative
model.
1.8 "Affiliate" means an entity that directly or indirectly controls, is
controlled by, or is under common control with a party, where "control" means
ownership or control of more than fifty percent (50%) of the voting interests
of that entity.
2. RESEARCH AND NON-COMMERCIAL LICENSE
Subject to Your continued compliance with this Agreement, BreezeBlue grants
You a limited, non-exclusive, worldwide, non-transferable, non-sublicensable,
royalty-free license under BreezeBlue's intellectual property rights in the
Model Materials to:
(a) access, use, reproduce, and modify the Model Materials;
(b) create Derivative Models; and
(c) distribute the Model Materials and Derivative Models as expressly
permitted by Section 4,
in each case solely for a Research Purpose or Non-Commercial Purpose.
No rights are granted except as expressly stated in this Agreement.
3. COMMERCIAL USE
No Commercial Purpose is permitted under this Agreement. Any Commercial
Purpose involving the Model Materials, a Derivative Model, or an Output
requires a separate written commercial license from BreezeBlue.
For clarity, this Agreement does not include a creator, content monetization,
small-business, revenue-threshold, or other implied commercial-use exception.
This Agreement governs only the open-weight Model Materials and their
self-hosted use. Outputs generated through BreezeBlue's hosted products or
APIs are governed by the applicable Terms of Service, plan terms, and any
separate written agreement, rather than this Agreement.
For commercial licensing inquiries, contact:
Website: https://breezeblue.ai
Email: contact@breeze.blue
4. DISTRIBUTION AND ATTRIBUTION
You may distribute the Model Materials or a Derivative Model solely for a
Research Purpose or Non-Commercial Purpose and only if You:
(a) provide every recipient with a complete copy of this Agreement and any
NOTICE file accompanying the Model Materials;
(b) retain all copyright, attribution, provenance, and proprietary notices;
(c) include the following notice in a NOTICE file distributed with the Model
Materials or Derivative Model:
"Breeze TTS 2 is licensed under the BreezeBlue Research and Non-Commercial
License Agreement. Copyright (c) 2026 RESONIA, INC. All Rights Reserved.";
(d) clearly identify any modifications You made and, for a Derivative Model,
state prominently in its model card, repository, and documentation:
"Derived from Breeze TTS 2 by BreezeBlue and licensed for research and
non-commercial use only.";
(e) license the distributed Model Materials or Derivative Model under this
Agreement without adding terms that conflict with or reduce the protections
of this Agreement; and
(f) ensure that each recipient independently accepts this Agreement before
accessing or using the Model Materials or Derivative Model.
You may not use "BreezeBlue," "Breeze TTS 2," or any confusingly similar name
as the primary name of a Derivative Model, product, or service, or in any way
that suggests endorsement, affiliation, official status, or successor status.
Reasonable descriptive attribution required by this Section is permitted.
Publication of non-commercial research results, benchmark results, and
illustrative samples in papers, reports, conference presentations, model
cards, repositories, or non-monetized demonstrations is permitted, provided
that You reasonably acknowledge Breeze TTS 2 and comply with this Agreement.
5. USE RESTRICTIONS
You will not, and will not permit any third party to:
(a) use the Model Materials, a Derivative Model, or any Output for a
Commercial Purpose without a separate written commercial license;
(b) use the Model Materials, a Derivative Model, or any Output to create,
train, fine-tune, distill, evaluate for training selection, or otherwise
improve any non-BreezeBlue foundational or generative speech, audio,
language, or multimodal model, except for creating a Derivative Model solely
for a Research Purpose or Non-Commercial Purpose under this Agreement;
(c) use the Model Materials, a Derivative Model, or any Output to clone,
simulate, imitate, or impersonate a real person's voice, identity, likeness,
or persona without that person's explicit and legally sufficient consent;
(d) submit or use reference audio, speaker embeddings, voice prompts,
recordings, performances, or other materials unless You have all rights,
licenses, permissions, and consents necessary for that use;
(e) use the Model Materials, a Derivative Model, or any Output to defraud,
deceive, harass, stalk, threaten, defame, exploit, or cause harm to any person;
(f) generate or distribute sexual, exploitative, or otherwise harmful content
involving a minor;
(g) engage in deceptive political persuasion, election interference, voter
suppression, synthetic robocalls, or false impersonation of a candidate,
public official, or other person in a political context;
(h) identify, authenticate, track, surveil, or profile a person using voice or
other biometric characteristics without a lawful basis and all consent
required by applicable law;
(i) distribute synthetic audio in circumstances where a reasonable person
would be materially misled about its origin or authenticity, or fail to make
any disclosure required by applicable law;
(j) remove, obscure, alter, or circumvent any copyright notice, attribution,
watermark, provenance signal, safety mechanism, or other proprietary notice
included in the Model Materials or Outputs;
(k) attempt to extract or reconstruct non-public training data, source data,
trade secrets, or proprietary components from the Model Materials, except to
the extent such a restriction is prohibited by applicable law; or
(l) use, export, re-export, transfer, or make available the Model Materials or
a Derivative Model in violation of any applicable law, regulation, export
control, or trade sanction.
Nothing in Section 5(k) prohibits ordinary inspection, loading, conversion,
quantization, modification, or fine-tuning of the released Model Materials as
expressly permitted by this Agreement.
6. LEGAL COMPLIANCE AND THIRD-PARTY RIGHTS
You are solely responsible for ensuring that Your use of the Model Materials,
Derivative Models, inputs, and Outputs complies with all applicable laws and
regulations and does not infringe or violate any third-party right, including
intellectual property, privacy, publicity, biometric privacy,
recording-consent, consumer-protection, election, and other applicable rights.
This Agreement grants no right to use, reproduce, clone, simulate, imitate,
or otherwise exploit any third-party voice, identity, likeness, persona,
performance, recording, copyrighted work, trademark, or other protected
material. You are solely responsible for obtaining all necessary rights,
licenses, permissions, notices, and consents.
BreezeBlue does not represent or warrant that any Model Material or Output is
cleared for Your intended use, unique, accurate, non-infringing, or suitable
for any particular purpose.
7. INTELLECTUAL PROPERTY
7.1 Model Materials. BreezeBlue and its licensors retain all right, title, and
interest in and to the Model Materials. Except for the limited license granted
in Section 2, no right or interest in the Model Materials is transferred to
You.
7.2 Derivative Models. As between You and BreezeBlue, You own the original
modifications You contribute to a Derivative Model, to the extent permitted by
applicable law. That ownership is subject to BreezeBlue's ownership of the
underlying Model Materials and to every restriction in this Agreement. A
Derivative Model remains governed by this Agreement.
7.3 Outputs. As between You and BreezeBlue, and to the extent permitted by
applicable law, You own Outputs You lawfully generate. Output ownership does
not remove or limit the non-commercial restrictions in this Agreement, grant
rights in third-party material, or authorize any use prohibited by this
Agreement.
7.4 Trademarks. No trademark license is granted except the limited right to
make accurate descriptive references required for attribution under Section
4. All goodwill arising from permitted use of BreezeBlue's marks belongs to
BreezeBlue.
7.5 Feedback. If You voluntarily provide suggestions, comments, or other
feedback about the Model Materials, You grant BreezeBlue a perpetual,
irrevocable, worldwide, royalty-free, fully paid, transferable, sublicensable,
non-exclusive license to use and exploit that feedback without restriction or
compensation.
7.6 Intellectual Property Claims. If You or Your Affiliate brings a claim or
legal proceeding alleging that the Model Materials, a Derivative Model, or an
Output infringes intellectual property rights owned or licensable by You or
Your Affiliate, the licenses granted to You under this Agreement terminate
automatically when the claim or proceeding is filed.
8. REPRESENTATIONS
You represent and warrant that:
(a) You have legal capacity and authority to enter into this Agreement;
(b) You will use and distribute the Model Materials, Derivative Models, and
Outputs only as permitted by this Agreement;
(c) You have all necessary rights and consents for Your inputs and intended
uses; and
(d) You are not prohibited from receiving or using the Model Materials under
applicable export-control, sanctions, or other laws.
9. DISCLAIMER OF WARRANTIES
TO THE MAXIMUM EXTENT PERMITTED BY APPLICABLE LAW, THE MODEL MATERIALS,
DERIVATIVE MODELS, OUTPUTS, AND ALL RELATED MATERIALS ARE PROVIDED "AS IS" AND
"AS AVAILABLE," WITH ALL FAULTS AND WITHOUT WARRANTIES OF ANY KIND, WHETHER
EXPRESS, IMPLIED, STATUTORY, OR OTHERWISE.
BREEZEBLUE DISCLAIMS ALL WARRANTIES, INCLUDING WARRANTIES OF TITLE,
NON-INFRINGEMENT, MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE,
ACCURACY, RELIABILITY, SECURITY, AND ANY WARRANTY THAT THE MODEL MATERIALS OR
OUTPUTS WILL BE ERROR-FREE, UNINTERRUPTED, UNIQUE, OR SUITABLE FOR YOUR USE.
YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS AND LAWFULNESS
OF YOUR USE AND ASSUME ALL RISKS ARISING FROM THAT USE.
10. LIMITATION OF LIABILITY
TO THE MAXIMUM EXTENT PERMITTED BY APPLICABLE LAW, BREEZEBLUE AND ITS
AFFILIATES, LICENSORS, OFFICERS, DIRECTORS, EMPLOYEES, CONTRACTORS, AND AGENTS
WILL NOT BE LIABLE UNDER ANY THEORY OF LIABILITY FOR ANY INDIRECT, INCIDENTAL,
SPECIAL, CONSEQUENTIAL, EXEMPLARY, OR PUNITIVE DAMAGES, OR FOR ANY LOSS OF
PROFITS, REVENUE, BUSINESS, GOODWILL, DATA, OR USE, ARISING OUT OF OR RELATING
TO THIS AGREEMENT, THE MODEL MATERIALS, ANY DERIVATIVE MODEL, OR ANY OUTPUT,
EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
TO THE MAXIMUM EXTENT PERMITTED BY APPLICABLE LAW, BREEZEBLUE'S TOTAL
AGGREGATE LIABILITY ARISING OUT OF OR RELATING TO THIS AGREEMENT WILL NOT
EXCEED ONE HUNDRED U.S. DOLLARS (US$100).
11. INDEMNIFICATION
You agree to defend, indemnify, and hold harmless BreezeBlue and its
Affiliates, licensors, officers, directors, employees, contractors, and agents
from and against any third-party claim, demand, action, proceeding, damage,
loss, liability, judgment, settlement, cost, or expense, including reasonable
attorneys' fees, arising out of or relating to:
(a) Your access to, use, modification, or distribution of the Model Materials
or a Derivative Model;
(b) Your inputs or Outputs;
(c) Your violation of this Agreement or applicable law; or
(d) Your infringement, misappropriation, or violation of any third-party
right.
12. TERM AND TERMINATION
This Agreement begins when You first access or use the Model Materials and
continues until terminated.
BreezeBlue may terminate this Agreement if You materially breach it. For a
material breach that is reasonably capable of cure, BreezeBlue will provide
written notice and at least thirty (30) days to cure before termination.
BreezeBlue may terminate immediately for a breach of Section 3, Section 5, or
applicable law, or where delay would reasonably create legal, security, fraud,
or safety risk.
Upon termination, You must immediately cease using and distributing the Model
Materials and Derivative Models, delete all copies under Your control, and,
upon reasonable request, confirm deletion in writing. Termination does not
require deletion of an Output lawfully created before termination, but no
Output may be used in violation of this Agreement or applicable law.
BreezeBlue may stop distributing the Model Materials prospectively. Such
discontinuation alone does not terminate rights already granted to a Licensee
that remains in compliance with this Agreement.
Sections 3, 5, 6, 7, 9, 10, 11, 12, and 13 survive termination to the extent
necessary to give them effect.
13. GOVERNING LAW AND JURISDICTION
This Agreement is governed by and construed in accordance with the laws of the
State of Delaware, without regard to its conflict-of-laws principles. The
United Nations Convention on Contracts for the International Sale of Goods
does not apply.
To the extent permitted by applicable law, any dispute arising out of or
relating to this Agreement shall be brought exclusively in the state or
federal courts located in the State of Delaware, and each party consents to
the personal jurisdiction and venue of those courts.
14. MISCELLANEOUS
14.1 Entire Agreement. This Agreement and any NOTICE file accompanying the
Model Materials constitute the entire agreement concerning the Model
Materials and supersede prior or contemporaneous understandings concerning
the same subject matter.
14.2 Separate Software Licenses. Source code and third-party components may be
made available under separate licenses. Those separate licenses govern only
the materials expressly identified as subject to them and do not grant any
right to use the Model Materials.
14.3 Assignment. You may not assign or transfer this Agreement or any right
under it without BreezeBlue's prior written consent. BreezeBlue may assign
this Agreement in connection with a merger, acquisition, reorganization, sale
of assets, or operation of law.
14.4 Severability. If any provision is held invalid or unenforceable, it will
be enforced to the maximum extent permitted, and the remaining provisions
will remain in effect.
14.5 No Waiver. Failure to enforce a provision is not a waiver of the right to
enforce it later.
14.6 No Endorsement. Nothing in this Agreement creates an agency,
partnership, joint venture, employment, fiduciary, sponsorship, or endorsement
relationship between the parties.
14.7 Updates. BreezeBlue may publish new versions of this Agreement. A new
version applies only if You expressly accept it or access Model Materials
released under that new version. Your continued use of a previously obtained
version of the Model Materials remains governed by the version You accepted,
unless applicable law requires otherwise.
15. CONTACT
Questions and commercial licensing requests may be sent to:
RESONIA, INC., doing business as BreezeBlue
Website: https://breezeblue.ai
Email: contact@breeze.blue
- Downloads last month
- 12
Quantized
Model tree for mchen04/Vireo-TTS-3B-MLX-bf16
Base model
BreezeBlue/Breeze-TTS-2