- Services
OpenVoice is MyShell’s open-weight voice cloning text-to-speech family with tone-color cloning from a short reference clip, MIT licensed for commercial use.
See all models from MyShellModels in family
2
Open weight
2
API only
0
Avg score
64.5
Top benchmark
90.8
TTS Arena
Total HF downloads
—
Primary modality
Audio
First release
Dec 2023
Latest release
Apr 2024
Every release in the OpenVoice family, ranked by composite score across benchmarks, popularity, efficiency, and versatility.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | audio | BB67.7 | — | Dec 2023 | |
| 2 |
When each release shipped, newest first. Useful for tracking version cadence.
Apr 17
Models with downloadable weights, ranked by composite score.
| # | Model | Modality | Score | Params | Released |
|---|---|---|---|---|---|
| 1 | audio | BB67.7 | — | Dec 2023 | |
| 2 |
The OpenVoice family is a series of AI models from MyShell. This page lists every release in the family with its benchmark scores, parameter count, and hardware requirements.
By composite score, OpenVoice is currently the top model in the family. For local inference, match the parameter count to your VRAM budget. For quality, pick the highest scorer that fits.
See the open-weight section above for models you can run locally. The API-only section lists closed releases that must be accessed through the provider’s API.
Spin up an instance in the cloud, or pick local hardware that fits.
Advertising disclosure: we earn commissions when you shop through the links below.
BB61.4 |
| — |
| Apr 2024 |
Dec 4
Composite grades across this family. Higher is better, blending benchmarks, popularity, and efficiency.
BB61.4 |
| — |
| Apr 2024 |
Vultr
GPU cloud with hourly and monthly plans, starting at $0.50/hr.
