---
license: mit
language:
- ja
pipeline_tag: text-to-speech
tags:
- text-to-speech
- speech
- tts
- character-image
base_model:
- Aratako/Irodori-TTS-500M-v2
- timm/vit_base_patch16_siglip_512.v2_webli
---
# Irodori-TTS-500M-v2-Character-Voice-SigLIP
[](https://character-voice-control.p1atdev.workers.dev/)
[](https://github.com/p1atdev/Irodori-Character-Voice)
[](https://huggingface.co/spaces/p1atdev/Irodori-TTS-500M-v2-Character-Voice-Demo)
## Model Description
**Irodori-TTS-500M-v2-Character-Voice-SigLIP** is a Japanese TTS model based on [Aratako/Irodori-TTS-500M-v2](https://huggingface.co/Aratako/Irodori-TTS-500M-v2).
This model synthesizes speech in a specific character's voice by using the **character's image** as a condition.
By using encoded features from a character image as the conditioning signal instead of reference audio or voice captions,
it enables zero-shot speech synthesis with a voice that matches the character's atmosphere.
This SigLIP variant uses [SigLIP-v2-B/16-512](https://huggingface.co/timm/vit_base_patch16_siglip_512.v2_webli) as the image encoder.
Another model in the same Character Voice family, [Irodori-TTS-500M-v2-Character-Voice-Tagger](https://huggingface.co/p1atdev/Irodori-TTS-500M-v2-Character-Voice-Tagger), uses a wd-tagger-based image encoder instead.
## Samples
> 遠くで鳴る夕暮れの鐘が、一日の終わりを告げている。家々の窓には、ぽつりぽつりと暖かな灯りがともり始めた。
| Character Image | Generated Audio |
| - | - |
| | |
| | |
| | |
| | |
| | |
| | |
## Usage
For inference code, installation instructions, the Gradio demo, and CLI examples, please refer to the GitHub repository.
- GitHub: [p1atdev/Irodori-Character-Voice](https://github.com/p1atdev/Irodori-Character-Voice)
- Demo Space: [Irodori-TTS-500M-v2-Character-Voice-Demo](https://huggingface.co/spaces/p1atdev/Irodori-TTS-500M-v2-Character-Voice-Demo)
For CLI inference, use `--hf-checkpoint p1atdev/Irodori-TTS-500M-v2-Character-Voice-SigLIP` together with `--character-image`.
See the GitHub README for complete command examples.
## License
This model is released under the MIT License.
## Acknowledgments
This model builds on the following projects and resources:
- [Aratako/Irodori-TTS-500M-v2](https://huggingface.co/Aratako/Irodori-TTS-500M-v2): base TTS model and architecture/codebase foundation
- [Aratako/Irodori-TTS](https://github.com/Aratako/Irodori-TTS): original implementation
- [Echo-TTS](https://jordandarefsky.com/blog/2025/echo/): architecture and training design reference for Irodori-TTS
- [Aratako/Semantic-DACVAE-Japanese-32dim](https://huggingface.co/Aratako/Semantic-DACVAE-Japanese-32dim): audio codec used by Irodori-TTS-500M-v2
- [timm/vit_base_patch16_siglip_512.v2_webli](https://huggingface.co/timm/vit_base_patch16_siglip_512.v2_webli): image encoder used by this SigLIP variant
We also thank the authors and contributors of the original Irodori-TTS project and related open-source projects.
## Citation
If you use this model in research or a project, please cite:
```bibtex
@misc{character-voice-control,
author = {Tingrui Zhou and Keiji Yanai},
title = {A Character's Look Speaks Volumes: Character Image-Conditioned Speaker Style Control for Japanese Text-to-Speech},
year = {2026},
eprint = {TODO},
archivePrefix = {arXiv},
primaryClass = {cs.SD},
url = {TODO}
}
```
Please also cite the original Irodori-TTS model:
```bibtex
@misc{irodori-tts-v2,
author = {Chihiro Arata},
title = {Irodori-TTS: A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control},
year = {2026},
publisher = {Hugging Face},
journal = {Hugging Face repository},
howpublished = {\url{https://huggingface.co/Aratako/Irodori-TTS-500M-v2}}
}
```
| |
| 
| |
| 
| |
| 
| |
| 
| |
| 
| |
## Usage
For inference code, installation instructions, the Gradio demo, and CLI examples, please refer to the GitHub repository.
- GitHub: [p1atdev/Irodori-Character-Voice](https://github.com/p1atdev/Irodori-Character-Voice)
- Demo Space: [Irodori-TTS-500M-v2-Character-Voice-Demo](https://huggingface.co/spaces/p1atdev/Irodori-TTS-500M-v2-Character-Voice-Demo)
For CLI inference, use `--hf-checkpoint p1atdev/Irodori-TTS-500M-v2-Character-Voice-SigLIP` together with `--character-image`.
See the GitHub README for complete command examples.
## License
This model is released under the MIT License.
## Acknowledgments
This model builds on the following projects and resources:
- [Aratako/Irodori-TTS-500M-v2](https://huggingface.co/Aratako/Irodori-TTS-500M-v2): base TTS model and architecture/codebase foundation
- [Aratako/Irodori-TTS](https://github.com/Aratako/Irodori-TTS): original implementation
- [Echo-TTS](https://jordandarefsky.com/blog/2025/echo/): architecture and training design reference for Irodori-TTS
- [Aratako/Semantic-DACVAE-Japanese-32dim](https://huggingface.co/Aratako/Semantic-DACVAE-Japanese-32dim): audio codec used by Irodori-TTS-500M-v2
- [timm/vit_base_patch16_siglip_512.v2_webli](https://huggingface.co/timm/vit_base_patch16_siglip_512.v2_webli): image encoder used by this SigLIP variant
We also thank the authors and contributors of the original Irodori-TTS project and related open-source projects.
## Citation
If you use this model in research or a project, please cite:
```bibtex
@misc{character-voice-control,
author = {Tingrui Zhou and Keiji Yanai},
title = {A Character's Look Speaks Volumes: Character Image-Conditioned Speaker Style Control for Japanese Text-to-Speech},
year = {2026},
eprint = {TODO},
archivePrefix = {arXiv},
primaryClass = {cs.SD},
url = {TODO}
}
```
Please also cite the original Irodori-TTS model:
```bibtex
@misc{irodori-tts-v2,
author = {Chihiro Arata},
title = {Irodori-TTS: A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control},
year = {2026},
publisher = {Hugging Face},
journal = {Hugging Face repository},
howpublished = {\url{https://huggingface.co/Aratako/Irodori-TTS-500M-v2}}
}
```