Hexgrad publishes Kokoro, an Apache-licensed text-to-speech model family that achieves high voice quality at sub-100M parameter counts, popular for on-device TTS.
Visit HexgradModels tracked
2
Open weight
2
API only
0
Avg score
73.8
Top benchmark
89.7
TTS Arena
Total HF downloads
22.4M
First release
Dec 2024
Latest release
Jan 2025
Ranked by composite score across benchmarks, popularity, efficiency, and versatility.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | audio | AA83.2 | — | Jan 2025 | |
| 2 | audio |
The strongest model from this provider in each modality. Click a card to open the model page.
How this provider’s catalog splits across text, image, video, audio, and embedding.
Models with downloadable weights, ranked by composite score.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | audio | AA83.2 | — | Jan 2025 | |
| 2 |
Each family is a model series. Browse all releases in a family with their own leaderboard.
Hexgrad ships 2 models that we track. Of those, 2 are open weight and 0 are accessed through their API.
It depends on the model. See the open-weight section above for models you can run locally, and the API-only section for closed models priced per token.
By composite score, Kokoro v1.0 is currently the top Hexgrad model in our directory. Composite score blends benchmarks, popularity, efficiency, and versatility.
Full Directory
Open the full directory to filter by hardware, capability, license, and benchmark score.
Or Browse by Family
See every release in a family side by side, with a timeline and a leaderboard. Useful when you have already picked a series and want the right size.
BB64.3 |
| — |
| Dec 2024 |
Dec 25
Composite grades across this provider’s catalog. Higher is better, blending benchmarks, popularity, and efficiency.
BB64.3 |
| — |
| Dec 2024 |
