---
title: IndexTTS-2.5-fp16
canonical_url: "https://www.modelscope.cn/models/mlx-community/IndexTTS-2.5-fp16"
md_url: "https://www.modelscope.cn/models/mlx-community/IndexTTS-2.5-fp16.md"
repository: mlx-community/IndexTTS-2.5-fp16
last_updated: 2026-09-03
license: other
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
base_model:
  - IndexTeam/IndexTTS-2.5
base_model_relation: finetune
parameters: 580.5M
tensor_type:
  - F16
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - zh
  - en
  - ja
  - es
  - ar
downloads: 468
stars: 1
tags:
  - mlx
  - tts
  - voice-cloning
  - indextts
  - apple-silicon
---

# IndexTTS-2.5-fp16

> IndexTTS-2.5-fp16 - mlx-community 在 ModelScope 开源的模型。IndexTTS-2.5 — MLX (fp16)

mlx-community/IndexTTS-2.5-fp16 是 ModelScope 魔搭社区上的 580.5M 参数text-to-speech模型，采用 other 许可，基于 IndexTeam/IndexTTS-2.5 构建。

- **Repository**: mlx-community/IndexTTS-2.5-fp16
- **License**: other
- **Tasks**: text-to-speech
- **Parameters**: 580.5M
- **Base model**: IndexTeam/IndexTTS-2.5
- **Tags**: mlx, tts, voice-cloning, indextts, apple-silicon
- **Downloads**: 468
- **Stars**: 1
- **Last updated**: 2026-09-03

Source: https://www.modelscope.cn/models/mlx-community/IndexTTS-2.5-fp16

---

# IndexTTS-2.5 — MLX (fp16)

MLX conversion of [IndexTeam/IndexTTS-2.5](https://huggingface.co/IndexTeam/IndexTTS-2.5)
(revision `d0aa86e75bb6f3437f3831e95056fa72842d89ef`) for Apple Silicon, re-hosted for the
[MLXEngine](https://github.com/xocialize/mlx-engine-swift) fleet. Consumed by
[mlx-indextts2-swift](https://github.com/xocialize/mlx-indextts2-swift) (Swift-MLX port,
Apache-2.0) and by [vanch007/mlx-indextts2](https://github.com/vanch007/mlx-indextts2)
(Python-MLX, MIT), whose converter (`convert_v25.py`, rev `4a32c967`) produced these tensors
with strict tensor-coverage verification (`conversion_report.json`).

## Files

| File | Component | dtype |
|---|---|---|
| `gpt.safetensors` | UnifiedVoice 2.5 GPT (24×1280, CAMPPlus speaker projection, language embedding, emotion conditioner) | fp16 |
| `codec.safetensors` | EnhancedCodec (Vocos/ConvNeXt encoder+decoder, 8192×8 FVQ) | fp16 |
| `s2mel.safetensors` | S2Mel — length regulator + DiT/CFM | fp16 |
| `bigvgan.safetensors` | BigVGAN v2 22 kHz 80-band 256× vocoder (NVIDIA, MIT) | fp16 |
| `multilingual_zh_ja_yue_char_del.tiktoken` | tiktoken BPE vocabulary (60 509 tokens incl. specials) | — |
| `model.safetensors` | facebook/w2v-bert-2.0 (MIT) — the semantic front-end, unchanged | fp32 |
| `config.yaml` / `config.json` / `model_manifest.json` / `conversion_report.json` | checkpoint config + conversion provenance | — |
| `feat1.pt` / `feat2.pt` / `wav2vec2bert_stats.pt` | emotion matrices + w2v-BERT feature stats (torch pickles, as upstream) | — |

## License

The model weights (`gpt`, `codec`, `s2mel`, the tokenizer and the feat/stats files) are
licensed under the **bilibili Model Use License Agreement** — see `LICENSE` (verbatim copy).
Commercial use is permitted; per §2.2 an entity whose products exceeded **100 million monthly
active users** in the preceding month or **RMB 1 billion annual revenue** in the preceding year
must request a separate license from bilibili. Downstream recipients are bound by the same
Agreement (§3.4(a)); retain the notices and this LICENSE with every copy (§3.4(b)).

`bigvgan.safetensors` is NVIDIA's BigVGAN v2 (MIT). `model.safetensors` is Meta's
w2v-bert-2.0 (MIT).

**Derivative-work statement (§4.1(a)):** Any modifications made to the original model in this
Derivative Work are not endorsed, warranted, or guaranteed by the original right-holder of the
original model, and the original right-holder disclaims all liability related to this
Derivative Work. (The modification here is a dtype conversion + tensor re-layout for MLX.)