What is Kokoro?
No dated launch filed yetApache-2.0
Summary
Apache-2.0 TTS model with 82 million parameters. Version 1.0, published January 27, 2025, lists 8 languages and 54 voices.
- Category
- Voice models
- Open source
- Yes
- License
- Apache-2.0
- Models
- Kokoro-82M
- Pricing
- Apache-2.0 weights. The model card says API hosts were under $1 per million characters as of April 2025. Self-hosting has no license fee.
- Links
- Website
Kokoro is the small model on this site. hexgrad/Kokoro-82M is 82 million parameters, Apache-2.0. The model card's version table lists v1.0 on January 27, 2025, with 8 languages and 54 voices. The card argues the size is enough to be useful and cheap to serve. It also notes, as of April 2025, that API hosts were charging under $1 per million characters. That is a market note on the card, not a price we negotiated.
Kokoro does not belong in a cloning shortlist. It belongs in a shortlist where CPU cost and a permissive license matter. Ranked in Best free AI voice models in 2026.
The alternatives field includes a slug that must exist. I referenced piper which I haven't created. I need to either create piper or remove it from alternatives.
I'll remove piper from kokoro alternatives and use qwen, chatterbox, voxcpm only. Let me fix that.
Kokoro alternatives
| Tool | License | Pricing note |
|---|---|---|
KokoroThis pageApache-2.0 TTS model with 82 million parameters. Version 1.0, published January 27, 2025, lists 8 languages and 54 voices. | Apache-2.0 | Apache-2.0 weights. The model card says API hosts were under $1 per million characters as of April 2025. Self-hosting has no license fee. |
Qwen3-TTSApache-2.0 speech models from the Qwen team, 0.6B and 1.7B, with voice clone, voice design, and 10 languages. | Apache-2.0 | Weights and code are Apache-2.0. No hosted price is quoted on the repository README we used. |
ChatterboxMIT-licensed TTS from Resemble AI. Chatterbox Multilingual V3 is a 500M model for 23 or more languages with zero-shot cloning. | MIT | The model card lists an MIT license. No API price is copied here. |
VoxCPMApache-2.0 tokenizer-free TTS from OpenBMB. VoxCPM2 is a 2B model with 30 languages, voice design, cloning, and 48 kHz output. | Apache-2.0 | Weights and code are Apache-2.0, including commercial use, per the repository. |
Launches and updates
No dated launch has been filed for Kokoro yet. The description above is from the project’s own pages.
Guides covering Kokoro
Questions
What is Kokoro?
Kokoro is an open-weight text-to-speech model with 82 million parameters, published on Hugging Face as hexgrad/Kokoro-82M under Apache-2.0. The v1.0 row is dated January 27, 2025, with 8 languages and 54 voices.
Does Kokoro clone voices?
The v1.0 model card describes preset languages and voices, not a zero-shot cloning API. For cloning, look at Qwen3-TTS, VoxCPM2, or Chatterbox.