indextts 1.5 needs about 0.9 GB of memory at Q4_K (a 0.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.3 GB to 2.3 GB.
Zero‑shot voice cloning TTS with 500M parameters
IndexTTS‑1.5 is a zero‑shot voice cloning system that converts reference audio and text into 24 kHz speech. The model uses a Conformer encoder, Perceiver resampler, GPT‑2 decoder, and BigVGAN vocoder. It is distributed under Apache‑2.0.
Good at
- Zero‑shot voice cloning
- Multilingual support for English and Chinese
- Beam search with num_beams=3
Limits
- No vision support
- Requires two GGUF files (GPT model and BigVGAN vocoder)
- Large memory for higher quant levels
Best for
- Cloning a new voice from a short audio clip
- Generating multilingual TTS without fine‑tuning
- Rapid prototyping of TTS pipelines
Who it’s for. Developers and researchers needing a lightweight, zero‑shot TTS solution. The model is suitable for applications that require quick voice cloning and multilingual synthesis without extensive training data.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q4_K | 0.4 GB | 0.9 GB | Fits | Get file → | |
| Q8_0 | 0.6 GB | 1.2 GB | Fits | Get file → | |
| — | 2.3 GB | 3.1 GB | Fits | Get file → |
For 8 GB VRAM, use the Q4_K quantized GPT model (0.36 GB) and the BigVGAN vocoder (0.27 GB). The Q8_0 quantized GPT model (0.64 GB) fits in 12 GB VRAM. The largest unknown quantized model (2.28 GB) requires at least 16 GB VRAM.
What GPU do you need for indextts 1.5?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (2.3 GB file, about 3.1 GB in use).
Which indextts 1.5 quant should you choose?
Q4_K (0.4 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is the first one in the table at 0.3 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about indextts 1.5
How much VRAM does indextts 1.5 need?
About 0.9 GB at Q4_K with an 8K context window. That is the 0.4 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run indextts 1.5 on an 8 GB GPU?
Yes, with the smaller files: the 2.3 GB file needs about 3.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of indextts 1.5 GGUF?
It depends on the quant: file is 0.3 GB, Q4_K is 0.4 GB, Q8_0 is 0.6 GB, file is 2.3 GB.
Where can I download indextts 1.5 GGUF?
The files are on Hugging Face in the cstr/indextts-1.5-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does indextts 1.5 use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run the Q4_K quantized model on 8 GB VRAM?
Yes, the Q4_K GPT model uses 0.9 GB memory at 8 k context and the BigVGAN vocoder uses 0.8 GB, fitting comfortably in 8 GB VRAM.
Does the model support Chinese voice cloning?
Yes, the model is trained on English and Chinese and supports cross‑language cloning.
Do I need external dependencies to run this model?
No, the SentencePiece tokenizer is embedded in the GGUF file and no external phonemizer is required.