Skip to content
SPECIFICTION
Get listed

KittenTTS

github.com

From $14.99/mo Free plan WebWindowsmacOSLinuxiOSAndroid
Visit github.com
Spec score 8.8 #24 of 223 in Text-to-Speech Software

Spec sheet

What it does
KittenTTS is an open-source text-to-speech library with a CPU-capable 1.7B-parameter KittenTTS 2 model and lightweight legacy models.Read 12 Oct 2026 · github.com
Intended users
The maker describes use cases including voice agents, customer-support call automation, content creation, and dedicated endpoints.Read 12 Oct 2026 · kittenml.com
Platforms
windows,macos,linux,apiRead 20 Sep 2026 · github.com
Integrations
The maker lists on-device SDKs for Python, Swift, React Native, Flutter, and Web, and says Kitten-TTS 2 SDKs are coming soon.Read 12 Oct 2026 · kittenml.com
Support
The maker offers commercial integration assistance, custom voice development, enterprise licensing, email support, GitHub Issues, and a Discord community.Read 12 Oct 2026 · github.com
API access
YesRead 20 Sep 2026 · github.com
Commercial use
YesRead 20 Sep 2026 · github.com
Export formats
WAVRead 20 Sep 2026 · github.com
Expression controls
Expression controls include emotion tags, inline vocal-event tags, and emphasis spans; the README labels emotion control beta and says its effect varies by voice and sentence.Read 12 Oct 2026 · github.com
Hosted API
The hosted API provides speech generation, voice cloning, and transcription endpoints, with OpenAI-compatible HTTP requests and streaming options.Read 12 Oct 2026 · kittenml.com
Local requirements
The README lists Linux, Windows, or Mac and Python 3.9 or later as system requirements for KittenTTS 2.Read 12 Oct 2026 · github.com
Model licensing
The repository code is Apache 2.0, while model weights have separate terms; KittenTTS 2 is listed under the Stellon Labs Community License.Read 12 Oct 2026 · github.com
Notable model limitation
The README says a single-pass whole script can truncate or drift into repetition, so long input is split into sentence-aware chunks.Read 12 Oct 2026 · github.com
Privacy and security
The privacy policy says the company collects service inputs including audio or voice recordings and outputs, and uses technical, physical, and organizational safeguards for personal data.Read 12 Oct 2026 · kittenml.com
Privacy limitation
The privacy policy says personal data may be transferred to jurisdictions with different protection levels, subject to due diligence and appropriate technical and organizational measures.Read 12 Oct 2026 · kittenml.com
Self-hosting
The maker says users can download the weights and self-host, including in a VPC, on-premises, or on-device for enterprise deployments.Read 12 Oct 2026 · kittenml.com
Voice cloning
KittenTTS 2 supports zero-shot voice cloning from a short audio sample without fine-tuning.Read 12 Oct 2026 · github.com
Voices and languages
The README lists 47 built-in voices and support for 20 languages.Read 12 Oct 2026 · github.com

Plans and prices

Free Free 30 free minutes of speech and transcription · Then $15 per 1M TTS characters and $1 per ASR audio hour · 36 voices · 10 languages · 5 ASR sessions and 2 TTS streams at once Read 12 Oct 2026 · kittenml.com
Pro $14.99 a month $179.88 billed annually $24.99 of usage included monthly · TTS: $0.65 per 1M characters · ASR: $0.10 per audio hour · Cancel anytime Read 12 Oct 2026 · kittenml.com
Enterprise Priced on request Custom usage and rates · Custom API capacity · Private deployment · Invoicing · Dedicated support and onboarding Read 12 Oct 2026 · kittenml.com

Every KittenTTS plan and price →

Where Specifiction places it

Alternatives to KittenTTSAll alternatives →