irodori tts voicedesign needs about 1.1 GB of memory at Q4_K (a 0.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.1 GB (F16) to 1.2 GB (F16).
Japanese TTS with multi‑modal voice design
Irodori‑TTS‑VoiceDesign is a 0.0707 billion‑parameter model based on a rectified‑flow diffusion transformer. It supports text, reference audio, and caption conditioning for Japanese speech synthesis. The model is released under MIT.
Good at
- Multi‑modal voice cloning
- Emoji‑based style control
- High‑quality Japanese TTS
Limits
- No vision support
- Requires 8 k context for estimates
- No explicit language list
Best for
- Voice cloning with style control
- Generating styled Japanese speech
- Audio watermarking via SilentCipher
Who it’s for. Developers building Japanese TTS applications that need flexible voice cloning and style control. Researchers exploring multi‑modal conditioning in diffusion models may also find it useful.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 0.1 GB | 0.7 GB | Fits | Get file → | |
| Q4_K | 0.6 GB | 1.1 GB | Fits | Get file → | |
| F16 | 1.2 GB | 1.9 GB | Fits | Get file → |
For 8 GB VRAM, use the Q4_K quant (file size 0.55 GB, memory 1.1 GB at 8 k context). If more VRAM is available, F16 (0.14 GB, 0.7 GB) gives higher precision. The largest F16 (1.24 GB, 1.9 GB) requires more memory.
What GPU do you need for irodori tts voicedesign?
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 (1.2 GB file, about 1.9 GB in use).
Which irodori tts voicedesign quant should you choose?
Q4_K (0.6 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is F16 at 0.1 GB, with the quality trade-offs that come with fewer bits. 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
Source
Frequently asked questions about irodori tts voicedesign
How much VRAM does irodori tts voicedesign need?
About 1.1 GB at Q4_K with an 8K context window. That is the 0.6 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 irodori tts voicedesign on an 8 GB GPU?
Yes, with F16: the 1.2 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of irodori tts voicedesign GGUF?
It depends on the quant: F16 is 0.1 GB, Q4_K is 0.6 GB, F16 is 1.2 GB.
Where can I download irodori tts voicedesign GGUF?
The files are on Hugging Face in the cstr/irodori-tts-voicedesign-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 irodori tts voicedesign 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 Q4_K quant uses about 1.1 GB memory at 8 k context, fitting within 8 GB VRAM.
What license does the model use?
MIT. The GGUF conversion retains the original MIT license.
Does the model support non‑Japanese languages?
No language list is provided; the model is designed for Japanese TTS.