RVC WebUI is a framework for training voice conversion models with short voice recordings.
Open source
24 alternativesKittenTTS
The KittenTTS project offers a text-to-speech model described as under 25 MB in size.
About KittenTTS
KittenTTS is an open-source Python text-to-speech library. It includes KittenTTS 2, a 1.7B-parameter model with voice cloning from short audio samples and expression tags, and lightweight ONNX models from 15M to 80M parameters, including a 25 MB int8 version.
It provides 47 built-in voices, support for 20 listed languages, and CPU-based inference through the same KittenTTS constructor. It requires Python 3.9 or later, about 6 GB of RAM on CPU, and about 1 GB of disk space, or 506 MiB with smaller weights.
Key features
- Clone a voice from 5-30 seconds of audio without fine-tuning
- 47 built-in voices including nine non-English options
- Supports 20 listed languages
- Expression control with emotion, event and emphasis tags
- Automatic expansion of numbers, dates, currencies and abbreviations
- 24 kHz audio output
Best for: Developers using Python who need CPU-based text-to-speech with cloning and multiple languages.
Good for
- Runs on CPU without requiring a GPU
- No Hugging Face login needed for model weights
- Includes a 25 MB int8 model option
Watch out for
- Requires Python 3.9 or later
- Needs about 6 GB of RAM on CPU or roughly 8 GB free on GPU
- Needs about 1 GB of disk space, or 506 MiB with smaller weights
KittenTTS at a glance
- Category
- AI & Machine Learning › AI Voice & Audio
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
KittenTTS alternatives
Tools and sites you could use instead, ranked by how closely they match.
EmotiVoice provides a multi-voice text-to-speech engine with prompt controls.
Open source
24 alternatives
The Chatterbox project provides an open-source text-to-speech system for speech generation.
Open source
24 alternatives
ESPnet includes tools for end to end speech processing and related speech tasks.
Open source
24 alternatives
MMAudio synthesizes audio from video and text through a multimodal joint-training approach presented at CVPR 2025.
Open source
19 alternatives
Audiblez creates audiobook files from EPUB e-books and offers a graphical interface.
Open source
19 alternativesPopular in AI Voice & Audio
Well-known listings from the same topic.
Google Illuminateilluminate.google.comAlteredaltered.aiELSA Speakelsaspeak.comKreadoAIkreadoai.comPodwisepodwise.aiAddsubtitleaddsubtitle.ai
KittenTTS FAQ
Does KittenTTS require a GPU?
No. The lightweight ONNX models run on CPU without a GPU, and KittenTTS 2 is described as running realtime on CPU.
How do I install it?
Run pip install kittenml with Python 3.9 or later. No Hugging Face login is needed.
What model sizes are available?
KittenTTS 2 is listed at 1.7B parameters and 506 MiB, and lightweight models range from 15M to 80M parameters, including a 25 MB int8 version.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.