🚀 MACE 1.3.0 Is Here

Introducing Text-to-Audio Generation, GPU Acceleration, Beat Syncing & More

MACE Version 1.3.0 is the biggest leap forward yet in MACE’s evolution. We’ve cracked open the next frontier: direct text-to-audio generation inside your DAW — powered by a new Prompt Engine, GPU acceleration across platforms, and a complete rework of how samples are managed and stored.
This update transforms MACE into not just a generative sampler — but a next level sound design interface for the modern producer. The Prompt Engine runs natively, on your own machine! No subscriptions, tokens, or cloud based processing or wait times.

Let’s dig into what’s new:

🧠 Prompt Engine: Text-to-Audio Inside Your DAW

The new Prompt Engine enables fully local, high-quality generation of sounds from simple text descriptions. No cloud needed. Just describe the sound — MACE takes care of the rest using machine learning diffusion models. This is a major technical milestone in plugin design!

Legacy models are still included as Fixed Models, ideal for one-shots. More on that below.

✍️ Prompt Editor Overlay

To launch the Prompt Overlay:

The Prompt Editor has various parameters:

Diffusion Steps

Use Raw Prompt is a feature that uses only the text in the prompt text-area. Some of the parameters in this editor inject guidance prompts under the hood to strengthen your average prompt. This is for advanced users that may want more granular control of the prompt for the generation.

Note: Due to the generative nature, not every generation is guaranteed to sound like your prompt or be the correct BPM. MACE tries its best to correct the BPM post generation if the BPM Sync Sample After Generation feature is ticked. Sometimes the results will be wildly different — however this can lead to happy accidents and glitchy fx!

📚 Prompt Library Integration

MACE 1.3.0 introduces a powerful Prompt Library system built directly into the Model Browser — letting you instantly browse, load, and trigger prompt-based generative models with zero typing required.

These curated categories give you fast access to pre-configured sounds across a wide creative spectrum:

🎨 Available Categories:

Each preset is handcrafted to generate unique sonic textures within its category — ranging from clean utility samples to experimental noise and cinematic textures.

You can also create and save your own prompt presets directly into these folders using the Prompt Editor — complete with author name, model name, and format controls.

Use the dropdown at the top of the Model Browser to explore the categories and drag any prompt directly into a cell to generate instantly.

🕘 Prompt Session History

Track every prompt you’ve used in a session — even across multiple MACE instances. Reuse, tweak, or relaunch any past prompt from the new Prompt Session History sidebar.

⚡ GPU Acceleration Across Platforms

MACE now runs faster and smarter on modern GPUs — no CUDA required.

No setup or drivers required. If MACE detects your GPU, it just works.

🧱 Fixed Models (Legacy Support)

Legacy generators are now labeled Fixed Models in the Model Browser. They don’t support prompts but are still:

These models work even on machines that can’t run the Prompt Engine. Ideal for quick stabs and percussion!

🔍 Advanced Waveform Viewer

The Advanced Waveform Viewer in MACE 1.3.0 has been overhauled for precision, performance, and clarity. Whether you’re fine-tuning loops, editing one-shots, or inspecting textures, this new viewer gives you detailed control and visual feedback.

Key Features:

🎛 Beat Snapping Workflow

Introducing 3 Snap Modes in the Sample View:

Bonus: Hold hotkeys while dragging loop markers:

📂 Generation Cache System

Every generated sample is now stored to disk instead of RAM — unlocking longer files, lower memory use, and persistent session data.

🛡️ Cache Management & Protection

Take control of your generation data:

🧠 Smart Tempo Sync & Resampling

🧩 UI & Plugin Enhancements

🐞 Bug Fixes & Stability

Thanks to everyone who tested the alpha builds and provided feedback — this release would not exist without you. 🙏
Let us know how it runs on your setup and keep pushing the boundaries of what MACE can do.

— Jordan / TENSOR

⚙ Development Update #3 ⚙

Hello all! 👋

It has been a while since an update, but I am happy to be back with a brand new MACE update (version 1.2.0) along with the new model training companion application ANVIL. I am still committed to improving and officially releasing MACE as well as new products!

It’s been a minute – I know some of you wondered if MACE was on hiatus. I’ve been deep in development, testing, and refactoring to rebuild MACE’s core engine for better stability, speed, and compatibility. Life happened, and so did a lot of technical challenges (hey, deploying ML-based plugins isn’t easy!). But I’m back, more committed than ever, and excited to share some huge updates with you including a new product ANVIL which will lead to a bunch of new expansion packs/models created by the community.

MACE v1.2.0 Update ⚡

This version addressed a lot of issues for some users that were having compatibility issues in certain DAW and includes brand new features that will elevate the instrument!

Quick Look At New Features👇

Instrument Mode / XY Morph Pad

Converts the first four cells into a 4 channel crossfader that plays melodically like an instrument. The X/Y Pad can of course be automated which makes for fun evolving basslines, weird glitchy pad fx, and all sorts of sonic madness. With the new looping mode engaged it can turn MACE into a wave scanning synthesizer!

Time Stretcher & Interpolation Playback Type

Each cell now has a Stretch and Ratio control in the main waveform view. The Ratio controls the percentage of stretch. (e.g. 0.5 = halving the sample and 2.0 is doubling). The time-stretching algorithm has a unique and gritty sound and four different types (Frequency Maps) that alter how the frequencies are stretched within the sample. Some of these can lead to wild and interesting results. The interpolation of the sample playback can also be optionally changed. Linear is the classic, gritty MACE sound while Cubic is a bit cleaner and refined.

Loop Playback Modes

When the Loop button is engaged in the main waveform view, that cell will enter Loop Mode. There are 3 different types: Forward, Backwards, and Ping-Pong. You can refine the start/end points of the sample. Try setting very short loops for fun granular type sounds — or set a long attack / release with a stretched sample in Ping-Pong mode for an evolving pad.

ANVIL Support

MACE 1.2.0 officially supports models trained by ANVIL. This allows for custom user trained models as well as longer audio generation! See below on further information about ANVIL or jump straight to the comprehensive introductory guide:

https://tensorpunk.com/anvil-getting-started-guide/

Full Release Notes 📝

Enhancements

New Features

New Hot Key Functions

Bugs Addressed


Important  Info About Mac Compatibility 💻

Expansion 1

13 New models have been included in this release 🔉

Introducing ANVIL – Companion training software for creating MACE models ⚔

ANVIL logo

A Standalone Machine Learning Platform 🎶

ANVIL is a standalone software solution, uniquely crafted to bring the power of machine learning into the hands of audio enthusiasts and creators. ANVIL is free software and a companion application to MACE. It allows you to create and curate your own datasets. These datasets can be used to create models that can be trained within ANVIL. You can then export these models for use within MACE!

A  full comprehensive introductory guide and further information can be found at:

https://tensorpunk.com/anvil-getting-started-guide/

ANVIL audio training software hyperparameters screen
Creating a model and tuning hyperparameters within ANVIL

ANVIL operates as a pre-packaged Python environment, boasting a user-friendly interface that simplifies the complex processes of audio data management and model training. With ANVIL, users can effortlessly create audio datasets and develop models capable of generating audio. These models are also compatible with MACE, further enhancing their utility.

A Commitment to Local Processing: Empowering Users with Direct Model Training 🔑

In a deliberate move away from cloud-based services, ANVIL is engineered to function locally on users’ machines. The vision of ANVIL is to empower users by enabling them to train their own models directly. This approach not only avoids the need for subscription fees associated with cloud computing but also aligns with our belief in harnessing the growing capabilities of average CPUs and GPUs. As hardware technology advances, we are confident that local machines will increasingly be able to handle the computational demands of sophisticated audio model training, making ANVIL an even more powerful tool in the hands of our users.

Requirements 💻

Navigating the Technical Landscape: Understanding ANVIL’s Requirements
As we strive to make ANVIL a versatile and powerful tool in the realm of audio machine learning, it’s important for users to understand the current technical requirements and our ongoing efforts towards broader compatibility.
Windows and NVIDIA Graphics Card: The Current Optimal Setup
At present, ANVIL is tailored for Windows operating systems. The software leverages the Pytorch machine learning environment, which requires CUDA support. Consequently, an NVIDIA graphics card is recommended for optimal performance. This setup ensures that users can fully utilize ANVIL’s capabilities for efficient and effective audio model training.
CPU Mode: Ensuring Universal Compatibility
Recognizing the diverse hardware configurations of our users, ANVIL also includes a CPU mode. While this mode ensures universal compatibility, it’s important to note that CPU processing is significantly slower compared to using a graphics card. We are committed to adapting ANVIL to various chip architectures and keeping pace with the evolving landscape of machine learning applications.
generating audio
Mac Version: Harnessing the Power of Silicon Chips
A Mac version of ANVIL is currently in development. The aim is to harness the capabilities of Apple’s silicon chips (M1, M2, and M3), which show promise in machine learning tasks when coupled with Metal Performance Shaders (MPS). This development marks a step towards expanding ANVIL’s reach and versatility.
AMD Graphics Cards on Windows: A Future Possibility
For users with AMD graphics cards on Windows, we acknowledge the current limitation due to Pytorch’s lack of support in this setup. However, we are closely monitoring the progress of ROCm support for Windows. We will attempt to integrate this feature into ANVIL as soon as it becomes feasible, aiming to open up more possibilities for our users.
Linux Users: A Potential Future Release
Lastly, for Linux enthusiasts, it’s worth noting that Linux currently supports ROCm/Pytorch. This compatibility opens up the potential for a Linux version of ANVIL, which we may pursue as an additional offering in the future.

Future of Tensorpunk, MACE, and ANVIL ⚔

I’m fully committed to pushing the evolution of MACE—and you can expect more frequent updates and expansion packs in the near future. I’m particularly excited about integrating new types of generative models into both MACE and ANVIL, along with a host of other innovative features. MACE is growing beyond its generative roots to become a truly unique instrument with its own sonic character, and I’m already working on the next wave of model and engine integrations.

As always, I welcome your ideas, presets, and custom models—let’s continue shaping the future of audio together! Join our Discord community to collaborate, experiment, and help shape the future of MACE and ANVIL. I would love to see more users sharing ANVIL trained models, tips and tricks for dataset preparation and model tuning. Your feedback and creativity are what drive Tensorpunk forward. Join Discord Now.

Thank you for sticking with me on this journey. I’m a one-person band here at Tensorpunk, passionately dedicated to delivering software, support, and a creating a community. As always, feel free to reach out with any questions or issues and I will do my best!

Jordan – Creator ✌

Feel free to reach out to me personally for any questions, ideas, or needed support: [email protected]

-Jordan Davis