Skip to content
SPECIFICTION
Get listed

Kokoro TTS

github.com

Free plan WebWindowsmacOSLinuxAPISelf-hosted
Visit github.com
Spec score 8.6 #41 of 223 in Text-to-Speech Software

What it is

Kokoro TTS is an open-weight text-to-speech model with 82 million parameters. It uses a decoder-only architecture built with StyleTTS 2 and ISTFTNet, and supports eight languages. In the documented Python pipeline, users can choose a voice and adjust speech speed; generated audio is 24 kHz and can be saved as WAV. The kokoro.js library runs the model locally in a browser through Transformers.js, also documents Node CPU use, and supports streaming speech as text is added. The model weights use the Apache license, and commercial use is listed as permitted. The maker describes Kokoro as lightweight and more cost-efficient than larger models while delivering comparable quality. Python installation uses kokoro, soundfile, and espeak-ng, with Misaki handling grapheme-to-phoneme processing. The README includes Windows setup guidance for espeak-ng and Apple Silicon GPU instructions for macOS M1 through M4. Examples point to Google Colab and a Hugging Face demo. Kokoro is free, with a free plan listed at free.

Spec sheet

Purpose
Kokoro is an open-weight text-to-speech model with 82 million parameters.Read 5 Oct 2026 · huggingface.co
Platforms
web,windows,macos,linux,api,self_hostedRead 20 Sep 2026 · github.com
Free plan
YesRead 20 Sep 2026 · github.com
Integrations
The maker provides examples using Google Colab and points to a Hugging Face demo; the model page also lists inference providers and notebooks.Read 5 Oct 2026 · github.com
Support
The repository links to a Discord community for Kokoro users and contributors.Read 5 Oct 2026 · github.com
License
The model weights are Apache-licensed, and the maker says Kokoro can be deployed in production or personal projects.Read 5 Oct 2026 · huggingface.co
API access
YesRead 20 Sep 2026 · github.com
Architecture
The model uses StyleTTS 2 and ISTFTNet and is decoder-only.Read 5 Oct 2026 · huggingface.co
Audio output
The Python example generates audio at 24 kHz and saves it as WAV files.Read 5 Oct 2026 · github.com
Commercial use
YesRead 20 Sep 2026 · github.com
Dependencies
The documented Python installation uses the kokoro package, soundfile, and espeak-ng; Kokoro uses Misaki for grapheme-to-phoneme processing.Read 5 Oct 2026 · github.com
Efficiency
The maker describes Kokoro as lightweight, faster, and more cost-efficient than larger models while delivering comparable quality.Read 5 Oct 2026 · huggingface.co
Export formats
WAVRead 20 Sep 2026 · github.com
JavaScript library
The kokoro.js library runs the model locally in a browser through Transformers.js and also documents Node CPU use.Read 5 Oct 2026 · github.com
Languages
8Read 20 Sep 2026 · github.com
Languages
The usage documentation lists American English, British English, Spanish, French, Hindi, Italian, Japanese, Brazilian Portuguese, and Mandarin Chinese.Read 5 Oct 2026 · github.com
Platform guidance
The README gives Windows installation guidance for espeak-ng and Apple Silicon GPU acceleration instructions for macOS M1 through M4.Read 5 Oct 2026 · github.com
Streaming
The JavaScript library documents streaming generated speech as text is added over time.Read 5 Oct 2026 · github.com
Training data
The model card says Kokoro was trained on permissive or non-copyrighted audio data and IPA phoneme labels, with a dataset of a few hundred audio hours.Read 5 Oct 2026 · huggingface.co
Voice and speed controls
The Python example selects a voice and sets speech speed through the pipeline.Read 5 Oct 2026 · github.com
Voice cloning
NoRead 20 Sep 2026 · github.com

Plans and prices

Kokoro open-weight model Free 82 million parameters · Apache-licensed weights Read 5 Oct 2026 · huggingface.co

Every Kokoro TTS plan and price →

Strong points and limits

Strong points

  • Free plan listed at free
  • Apache-licensed weights; commercial use permitted
  • Eight languages and WAV output
  • Browser-local and Node CPU use documented
  • Voice selection and speech speed controls

Limits

  • Voice cloning is not supported
  • Python setup requires soundfile and espeak-ng
  • WAV is the listed export format

Who it suits

Kokoro suits developers and creators who want an open-weight speech model for personal or production projects, including commercial use. Its browser and Node options may suit users who want local inference, while Python setup is also documented.

Verdict

Kokoro pairs open-weight licensing with Python and JavaScript routes, including browser-local use and streaming. It does not offer voice cloning, and the listed audio export format is WAV.

Where Specifiction places it

Alternatives to Kokoro TTSAll alternatives →