---
title: IndexTTS-2.5-AIPod
canonical_url: "https://www.modelscope.cn/models/manateelazycat/IndexTTS-2.5-AIPod"
md_url: "https://www.modelscope.cn/models/manateelazycat/IndexTTS-2.5-AIPod.md"
repository: manateelazycat/IndexTTS-2.5-AIPod
last_updated: 2026-10-28
license: other
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
parameters: 580.5M
tensor_type:
  - F32
library_name:
  - safetensors
downloads: 15
stars: 0
---

# IndexTTS-2.5-AIPod

> IndexTTS-2.5-AIPod - manateelazycat 在 ModelScope 开源的模型。IndexTTS 2.5 model, Jetson runtimes and minimal LPK release

manateelazycat/IndexTTS-2.5-AIPod 是 ModelScope 魔搭社区上的 580.5M 参数text-to-speech模型，采用 other 许可。

- **Repository**: manateelazycat/IndexTTS-2.5-AIPod
- **License**: other
- **Tasks**: text-to-speech
- **Parameters**: 580.5M
- **Downloads**: 15
- **Stars**: 0
- **Last updated**: 2026-10-28

Source: https://www.modelscope.cn/models/manateelazycat/IndexTTS-2.5-AIPod

---

# IndexTTS 2.5 for AI Pod

IndexTTS 2.5 inference code and models retain their upstream licenses.
Auxiliary W2V-BERT, BigVGAN, CAMPPlus, UniDic, and runtime dependencies retain
component-specific terms. Original notices accompany the model snapshot and
licenses/dependency-notices-0.1.0.tar.gz. UniDic is external model content.
The Orin and Thor Docker-save runtimes contain inference code and dependencies
without model weights, dictionaries, compilers or download caches. The LPK is a
minimal bootstrap for the separately hosted complete controller.
Source: https://github.com/index-tts/index-tts/tree/39207d91c30899cad1e7c1b9eb678c241f678e55