mlx-indextts2-2.5-fp32

IndexTTS 2.5 converted to native MLX weights for Apple Silicon. Use it with vanch007/mlx-indextts2.

Variant

  • Precision / quantization: fp32
  • Approximate local size: 4.0GB
  • Source model: IndexTeam/IndexTTS-2.5
  • Source revision: d0aa86e75bb6f3437f3831e95056fa72842d89ef
  • Conversion status: strict manifest pass
  • Details: All GPT, EnhancedCodec, S2Mel/DiT, and BigVGAN floating weights use float32.

The model supports Chinese, English, Japanese, Spanish, and Arabic, including cross-lingual voice transfer, separate speaker/emotion references, manual and text-derived emotion control, and Pinyin/CMU/Kana pronunciation annotations.

Download and Run

git clone https://github.com/vanch007/mlx-indextts2.git
cd mlx-indextts2
uv sync --extra v25

hf download vanch007/mlx-indextts2-2.5-fp32 \
  --local-dir models/mlx-indextts2-2.5-fp32

uv run mlx-indextts generate \
  --profile v25 \
  -m models/mlx-indextts2-2.5-fp32 \
  --language zh \
  -r /path/to/reference.wav \
  -t "你好,这是 IndexTTS 2.5 的 MLX 推理测试。" \
  -o output.wav

See the project README and IndexTTS 2.5 guide for batch, API, WebUI, streaming, duration, pronunciation, and emotion-control examples.

Included Files

  • gpt.safetensors
  • codec.safetensors
  • s2mel.safetensors
  • bigvgan.safetensors
  • multilingual_zh_ja_yue_char_del.tiktoken
  • config.yaml and config.json
  • model_manifest.json and conversion_report.json
  • reference preprocessing statistics/features
  • LICENSE

The runtime additionally resolves the manifest-declared facebook/w2v-bert-2.0 and funasr/campplus preprocessing dependencies.

Validation Boundary

The converted component coverage and strict load checks passed. The project validation matrix also covers five-language synthesis, ASR sanity checks, speaker similarity, emotion modes, cross-lingual generation, batch/API/WebUI, and completed-segment streaming. Results are hardware- and sample-specific; human listening remains recommended before production use.

License and Derivative Notice

The repository code is MIT-licensed, but these converted model weights are a Derivative Work governed by the included bilibili Model Use License Agreement. Review its commercial thresholds, downstream obligations, use restrictions, and prohibited high-risk scenarios before downloading or using the model.

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.

Downloads last month
15
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for vanch007/mlx-indextts2-2.5-fp32

Finetuned
(3)
this model