Local TTS model
Kitten TTS
Tiny open-source TTS built for edge devices. Three variants: 80M, 40M, and 14M params - the smallest fits in under 25 MB. Highly expressive despite its size. Runs entirely on CPU, no GPU required. Perfect for embedded systems, mobile, and offline apps.
Edge ready
text-to-speech generation
1 languages
Apache 2.0
Quality
7.5/10
Speed
10/10
Model size
0.025 GB
Voices
Built-in expressive voice
Can Kitten TTS run locally?
Kitten TTS can generate speech locally for private voice workflows. Start with pip install kitten-tts.
Apache 2.0 license. Still verify upstream usage notes before shipping.
pip install kitten-tts
Upstream source
realtimelow-latency
Audio profile
Best fit
Kitten TTS is best for fast on-device voice responses and local assistants.
Hardware: cpuedgeapple
Model details
Type
Local TTS model
Family
kitten
Latency
ultra-low
Formats
onnxpytorch
Languages
en
Context
3 variants: 80M / 40M / 14M params
Install locally
01
Check runtimeConfirm the backend supports onnx, pytorch on your machine.02
Install modelUse the upstream command or repository instructions.03
Test locallyRun a short private audio prompt before moving into production workflows.pip install kitten-tts
Good for
- text-to-speech generation
- Edge ready local workflows
- realtime, low-latency
Watch before shipping
- Validate pronunciation, latency and artifacts with your own voice samples.
- Review the upstream license and acceptable-use notes.
- Benchmark on your target CPU, Apple Silicon or GPU setup.
Related TTS and speech models
hexgrad
Kokoro TTS
Local TTS model · Q 9.2 · Speed 9.8
Kyutai
Moshi
Local TTS model · Q 9 · Speed 9.5
Neuphonic
NeuTTS Air
Local TTS model · Q 9 · Speed 9.5
Microsoft Research
VibeVoice Realtime 0.5B
Local TTS model · Q 9.1 · Speed 9.2
Supertone
Supertonic 3
Local TTS model · Q 8.8 · Speed 9.8
OpenMOSS / MOSI.AI
MOSS-TTS-Nano
Local TTS model · Q 8.5 · Speed 9.7
OuteAI
OuteTTS
Local TTS model · Q 8.7 · Speed 8.5
Rhasspy
Piper
Local TTS model · Q 7.5 · Speed 10