EC

Echo-TTS

EchoGGUF by dignomeUpdated 2026-08-28
Download on Hugging Face
Parameters2.77B
Context—
Layers—
Architectureecho_tts
Smallest quant3.0 GB
Quick answer

Echo-TTS needs about 3.9 GB of memory at Q8_0 (a 3.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 3.0 GB (Q8_0) to 5.5 GB (F16).

Echo‑TTS: a 2.77 B diffusion‑based text‑to‑speech model

Echo‑TTS is a diffusion‑based text‑to‑speech model with 2.77 billion parameters. The model is released under CC‑BY‑NC‑SA‑4.0 and is intended for research and non‑commercial use. It supports the s1 codec weights and is available in Q8_0 and F16 quantisations.

Good at

  • Diffusion‑based TTS synthesis
  • Research‑grade audio generation
  • Non‑commercial audio projects

Limits

  • No vision support
  • License restricts commercial use
  • No support for deception or impersonation

Best for

  • Academic TTS research
  • Non‑commercial audio synthesis
  • Prototype voice applications

Who it’s for. Researchers and developers working on text‑to‑speech research who need a diffusion‑based model and are compliant with CC‑BY‑NC‑SA‑4.0 licensing. The model is suitable for non‑commercial projects and prototyping.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_03.0 GB 3.9 GB
Fits Get file →
F165.5 GB 6.7 GB
Fits Get file →

For 8 GB VRAM, use the Q8_0 quantised file (3.03 GB, ~3.9 GB memory at 8k context). If more VRAM is available, the F16 quantised file (5.55 GB, ~6.7 GB memory at 8k context) provides higher precision.

What GPU do you need for Echo-TTS?

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 Q8_0 (3.0 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.0 GB file, about 3.9 GB in use).
  • 8 GB VRAM: the best quant that fits is F16 (5.5 GB file, about 6.7 GB in use).

Which Echo-TTS quant should you choose?

Q8_0 (3.0 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureecho_tts
Parameters2.77B

Source

Quantized bydignome
FamilyEcho
Downloads (HF)68,451
Last updated2026-08-28

Frequently asked questions about Echo-TTS

How much VRAM does Echo-TTS need?

About 3.9 GB at Q8_0 with an 8K context window. That is the 3.0 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 Echo-TTS on an 8 GB GPU?

Yes, with F16: the 5.5 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Echo-TTS GGUF?

It depends on the quant: Q8_0 is 3.0 GB, F16 is 5.5 GB.

Where can I download Echo-TTS GGUF?

The files are on Hugging Face in the dignome/Echo-TTS repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Echo-TTS use?

Hugging Face lists the license as cc-by-nc-sa-4.0. 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 Echo‑TTS on 8 GB VRAM?

Yes, the Q8_0 quantised file requires about 3.9 GB memory at 8k context, which fits within 8 GB VRAM.

Is Echo‑TTS suitable for commercial products?

No, the model is licensed under CC‑BY‑NC‑SA‑4.0, which prohibits commercial use.

Does Echo‑TTS support voice cloning?

The model is not designed for voice cloning and is restricted from generating audio that mimics a real person’s voice without consent.

Similar models

Browse all →

More from dignome

All by dignome →

More Echo models

All Echo →

Other tiny models

All tiny models →