What is KittenTTS built with?

Q: Which repos have a stack like KittenTTS's?

The ones that share most of its stack: mudler/LocalAI, ray-project/ray, and gradio-app/gradio.

KittenTTS is a Python repo built with FastAPI. It uses AI through NVIDIA, nvidia-cudnn-cu12, onnxruntime-gpu, torch, safetensors, and 8 more and uses Hugging Face. It has 16,429 written lines, with 9 test files.

Read on November 7, 2026, at commit b9517e3. Read it as markdown

Backend

The base 1

FastAPI

AI 13

torch15 files
safetensors6 files
librosa3 files
diffusers2 files
torchaudio2 files
NVIDIA
transformers5 files
einops2 files
onnxruntime1 file
phonemizer1 file
s3tokenizer1 file
nvidia-cudnn-cu12

1 more

onnxruntime-gpu

Services 1

Hugging Face4 files · kittenml/get_model.py, line 9

Support

Other 9

NumPy13 files
omegaconf2 files
SciPy1 file
brotli
hydra-core
soundfile12 files
espeakng-loader1 file
pyloudnorm
resemble-perth

Other repos with a similar stack

Ordered by how much of its stack they share with KittenTTS, then by stars.

mudlerLocalAI
50.2k
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
13 of 24 in common · GoCompare →
ray-projectray
44.2k
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
9 of 24 in commonCompare →
gradio-appgradio
44k
Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
9 of 24 in commonCompare →
vllm-projectvllm
96.3k
A high-throughput and memory-efficient inference and serving engine for LLMs
8 of 24 in commonCompare →
unslothaiunsloth
79.1k
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
8 of 24 in commonCompare →
jamiepinevoicebox
59.4k
The open-source AI voice studio. Clone, dictate, create.
8 of 24 in common · TypeScriptCompare →

Frequently asked questions

What language is KittenTTS written in?

KittenTTS is written in Python, with 16,429 written lines.

What framework does KittenTTS use?

KittenTTS is built with FastAPI.

Does KittenTTS use AI?

Yes. KittenTTS uses AI through NVIDIA, nvidia-cudnn-cu12, onnxruntime-gpu, torch, safetensors, transformers, librosa, diffusers, einops, torchaudio, onnxruntime, phonemizer, and s3tokenizer.

What services does KittenTTS use?

KittenTTS uses Hugging Face.

The proof: kittenml/get_model.py, line 9

Does KittenTTS have tests?

Yes. KittenTTS has 9 test files.

Which repos have a stack like KittenTTS's?

The ones that share most of its stack:mudler/LocalAI ray-project/ray gradio-app/gradio