PI

piper en US lessac medium

PiperGGUF by cstrUpdated 2026-08-03
Download on Hugging Face
Parameters16M
Context—
Layers—
Architecturepiper
Smallest quant0.0 GB
Quick answer

piper en US lessac medium needs about 0.5 GB of memory at F16 (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU.

Piper en_US lessac medium voice for text‑to‑speech

This is a small VITS‑based TTS voice converted to GGUF format. It contains 0.0157 billion parameters and is licensed under MIT. The only available quantization is F16, with a file size of 0.03 GB.

Good at

  • Small footprint TTS
  • High‑quality 22.05 kHz mono output
  • Easy integration with CrispASR

Limits

  • No vision or multimodal support
  • Only F16 quant available
  • No training or fine‑tuning included

Best for

  • Embedded TTS applications
  • Low‑resource voice synthesis
  • Rapid prototyping of speech systems

Who it’s for. Developers needing a lightweight, open‑source TTS voice for English (US) applications. Suitable for IoT devices, voice assistants, and research projects that require a small, MIT‑licensed model.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.0 GB 0.5 GB
Fits Get file →

The F16 quantization is the only format available. It requires approximately 0.5 GB of VRAM at 8 k context. For systems with limited memory, this model remains the best choice as no other quantizations exist.

What GPU do you need for piper en US lessac medium?

These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is F16 (0.0 GB file, about 0.5 GB in use).

Which piper en US lessac medium quant should you choose?

F16 (0.0 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturepiper
Parameters16M

Source

Quantized bycstr
FamilyPiper
Licensemit
Downloads (HF)1,128
Last updated2026-08-03

Frequently asked questions about piper en US lessac medium

How much VRAM does piper en US lessac medium need?

About 0.5 GB at F16 with an 8K context window. That is the 0.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run piper en US lessac medium on an 8 GB GPU?

Yes, with F16: the 0.0 GB file needs about 0.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of piper en US lessac medium GGUF?

It depends on the quant: F16 is 0.0 GB.

Where can I download piper en US lessac medium GGUF?

The files are on Hugging Face in the cstr/piper-en_US-lessac-medium-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does piper en US lessac medium use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, the F16 quant requires about 0.5 GB of VRAM at 8 k context, well within an 8 GB budget.

Does this model support multiple languages?

No, the model is designed for English (US) only.

Is the model suitable for training new voices?

No, it is a pre‑converted GGUF file; training or fine‑tuning is not provided.

Other GGUFs of piper-voices

Similar models

Browse all →

More from cstr

All by cstr →

More Piper models

All Piper →

Other tiny models

All tiny models →