---
title: scenema-audio
canonical_url: "https://www.modelscope.cn/studios/AI-ModelScope/scenema-audio"
md_url: "https://www.modelscope.cn/studios/AI-ModelScope/scenema-audio.md"
repository: AI-ModelScope/scenema-audio
last_updated: 2026-06-16
sdk_type: gradio
sdk_version: 6.2.0
downloads: 0
stars: 19
---

# scenema-audio

> scenema-audio - AI-ModelScope 在 ModelScope 创建的在线 Demo。Scenema Audio (ZeroGPU)

AI-ModelScope/scenema-audio 是 ModelScope 魔搭社区上的在线可交互 Demo（创空间），基于 gradio 6.2.0 构建。

- **Repository**: AI-ModelScope/scenema-audio
- **SDK**: gradio
- **SDK version**: 6.2.0
- **Downloads**: 0
- **Stars**: 19
- **Last updated**: 2026-06-16

Source: https://www.modelscope.cn/studios/AI-ModelScope/scenema-audio

---

# Scenema Audio (ZeroGPU)

Gradio wrapper around [ScenemaAI/scenema-audio](https://github.com/ScenemaAI/scenema-audio).

Zero-shot expressive voice cloning and speech generation with emotion, pacing,
and breath control, built on an audio diffusion transformer extracted from
[LTX 2.3](https://github.com/Lightricks/LTX-2).

## Cold start

First request downloads ~38 GB of model weights:
- `scenema-audio-transformer-int8.safetensors` (~4.9 GB)
- `scenema-audio-pipeline.safetensors` (~6.7 GB)
- `google/gemma-3-12b-it` (~24 GB, **gated** — requires `HF_TOKEN` secret)
- SeedVC + BigVGAN + Whisper checkpoints (~3 GB)
- MelBandRoFormer (~436 MB)

Set `HF_TOKEN` in the Space secrets with access to `google/gemma-3-12b-it`.

## License

- **Model weights:** LTX-2 Community License Agreement
- **Code:** MIT