kitten tts 2 needs about 2.5 GB of memory at its main file (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
1.7B Qwen3 TTS model with in‑context voice cloning
Kitten TTS 2 is a 1.7 B parameter speech language model based on Qwen3. It generates S3 codec tokens that a vocoder converts to 24 kHz audio. The model supports 115 voices across 16 languages and includes emotion and emphasis controls.
Good at
- In‑context voice cloning
- Multilingual voice synthesis
- Emotion and emphasis control
Limits
- No vision support
- Requires 8 k context for full performance
- License type unknown
Best for
- Creating custom voice assistants
- Generating audiobooks with varied emotions
- Embedding TTS in local applications
Who it’s for. Developers needing a lightweight, local TTS solution with voice cloning and expressive controls. The model is suitable for offline use without Hugging Face login.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 1.0 GB | 2.5 GB | Fits | Get file → |
The only available GGUF file is 1.03 GB with an estimated 2.5 GB memory at 8 k context. This is the recommended version for systems with at least 4 GB RAM. No other quants are listed, so use this file for all deployments.
What GPU do you need for kitten tts 2?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 (1.0 GB file, about 2.5 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about kitten tts 2
How much VRAM does kitten tts 2 need?
About 2.5 GB at its main file with an 8K context window. That is the 1.0 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 kitten tts 2 on an 8 GB GPU?
Yes, with the smaller files: the 1.0 GB file needs about 2.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of kitten tts 2 GGUF?
It depends on the quant: file is 1.0 GB.
What context length does kitten tts 2 support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download kitten tts 2 GGUF?
The files are on Hugging Face in the KittenML/kitten-tts-2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does kitten tts 2 use?
Hugging Face lists the license as other. 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 Kitten TTS 2 on 4 GB RAM?
Yes, the 1.03 GB GGUF file uses about 2.5 GB RAM at 8 k context, fitting within a 4 GB system.
Does the model support non‑English voices?
Yes, it includes 115 voices, 16 of which are named for specific languages such as Spanish, Japanese, and Russian.
How do I control emotion in the output?
Use leading tags like [angry] or inline tags such as `(((emphasis)))` to steer delivery.