Suggestions appear as you type. Use the up and down arrows to choose one and Enter to open it.

This page's audience our own tag's counts — open to see them
–Visits
–Page views
–Clicks to vendors
–Time on page
–Reading now
Clicks to vendors, by tool
  • –
Top countries
  • –
Devices
  • –

– · visits, page views and clicks counted by our own tag, which counts more than our checked analytics; every figure rounded down · how we count

KittenTTS review

Free#172 of 222 in Text-to-Speech Software

A practical local TTS library for developers who want CPU inference and simple WAV output.

3.0/10Editor score
Visit KittenTTS
KittenTTS3.0 Visit KittenTTS

Reviewed by iTechGuides Editors · Editorial team · Updated Oct 2026

KittenTTS is an open-source text-to-speech library for developers building local or edge voice features. Built on ONNX, it offers lightweight models ranging from 15M to 80M parameters and supports CPU inference without requiring a GPU. The project runs on Linux, macOS, and Windows, and also provides API access. Its eight preset voices, adjustable speech speed, Python API, and WAV generation make it suited to small deployments, scripted narration, and product integrations where local processing matters.

Its feature set focuses on a straightforward developer workflow rather than broad voice coverage. Text preprocessing handles numbers, currencies, and units before synthesis, while output is available at 24 kHz and can be saved as WAV files. This combination gives developers practical controls for predictable speech generation, but the narrower voice and language breadth may not fit projects that need extensive localization or a large voice catalog. Commercial support is available for product integrations and enterprise licensing, adding an option for teams moving beyond a small local deployment.

The main consideration is the maturity of the developer interface. The project README labels the APIs as a developer preview and says they may change between releases, so teams should account for potential maintenance when integrating KittenTTS into a longer-lived product. Choose it for CPU-friendly, open-source inference with Python control and local WAV output. Consider an alternative when broader voice or language coverage, a more stable API surface, or additional export formats are central requirements.

KittenTTS pros and cons

  • Where it wins
    • CPU inference works without requiring a GPU
    • Eight built-in voices with adjustable speech speed
    • Python API, preprocessing, and WAV generation for local workflows
  • Where it doesn't
    • Voice and language breadth is limited
    • Published APIs are labeled as a developer preview
    • Audio export is limited to WAV

KittenTTS fact sheet, pricing and score →

Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. Bought places stand at the number bought; this page and our disclosure say so. Paying vendors may get a fuller, more detailed review from our editors, and that review can change their score. How we rank.

Last updated · How we research and update