Audio modelActive
Kokoro-82M
hexgrad
- Released
- December 25, 2024
- Data date
- September 24, 2026
- Model class
- Access
Kokoro-82M is a local open-weight TTS checkpoint with 82 million parameters. The weights use Apache 2.0, and v1.0 lists eight languages, 54 voices, and a 24 kHz sample rate. The architecture uses StyleTTS 2 and ISTFTNet in a decoder-only setup without a released diffusion or encoder component.
Specifications and access
| Specification | Value and source |
|---|---|
| Model class | Text-to-speechSource |
| Access | Local executionSource |
| Model ID | hexgrad/Kokoro-82MSource |
| Input | TextSource |
| Output | AudioSource |
| Task | Local speech generationSource |
| Supported details | 82 million parameters, Apache-2.0 licenseSource |
| Version 1.0 | v1.0: January 27, 2025Source |
| Languages and voices | 8 languages and 54 voices in v1.0Source |
| Sample rate | 24 kHzSource |
Popularity
50.9 / 100
Sources and data date
| Type | Evidence and data date |
|---|---|
| Additional source | Kokoro model card (retrieved September 24, 2026) · Kokoro-82M model card · Editorial description reviewed October 2, 2026 |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Creative Commons Attribution 4.0 |