- Home
- Text-to-Speech Software
- KittenTTS
On the recordRead 12 Oct 202618 facts
KittenTTS
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
Read 12 Oct 2026 · kittenml.com
Pro
$14.99a month, billed yearly
$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
Read 12 Oct 2026 · kittenml.com
On the record
- API access
- Yesgithub.com · read 20 Sep 2026
- Commercial use
- Yesgithub.com · read 20 Sep 2026
- Export formats
- WAVgithub.com · read 20 Sep 2026
- 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.github.com · read 12 Oct 2026
- Hosted API
- The hosted API provides speech generation, voice cloning, and transcription endpoints, with OpenAI-compatible HTTP requests and streaming options.kittenml.com · read 12 Oct 2026
- Integrations
- The maker lists on-device SDKs for Python, Swift, React Native, Flutter, and Web, and says Kitten-TTS 2 SDKs are coming soon.kittenml.com · read 12 Oct 2026
- Intended users
- The maker describes use cases including voice agents, customer-support call automation, content creation, and dedicated endpoints.kittenml.com · read 12 Oct 2026
- Local requirements
- The README lists Linux, Windows, or Mac and Python 3.9 or later as system requirements for KittenTTS 2.github.com · read 12 Oct 2026
- 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.github.com · read 12 Oct 2026
- 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.github.com · read 12 Oct 2026
- 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.kittenml.com · read 12 Oct 2026
- 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.kittenml.com · read 12 Oct 2026
- 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.kittenml.com · read 12 Oct 2026
- Support
- The maker offers commercial integration assistance, custom voice development, enterprise licensing, email support, GitHub Issues, and a Discord community.github.com · read 12 Oct 2026
- Voice cloning
- KittenTTS 2 supports zero-shot voice cloning from a short audio sample without fine-tuning.github.com · read 12 Oct 2026
- Voices and languages
- The README lists 47 built-in voices and support for 20 languages.github.com · read 12 Oct 2026
- 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.github.com · read 12 Oct 2026
