| Price from | Free | — |
| Free plan | Yes | — |
| Free trial | — | — |
| Open source | — | — |
| Web | Yes | Yes |
| Windows | Yes | — |
| Linux | Yes | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 1 | 0 |
| Spec score · AI voice cloning tools | 8.8 (#9) | 7.6 (#33) |
| Deployment | The project documents a local WebUI, a Python API, and production serving through a vLLM recipe. | The README says it can be deployed on AWS, GCP, or Azure, or used locally with the reference implementation. |
| Interfaces | The repository provides a browser-based WebUI and a Python API for inference. | The repository provides a web UI and an inference server with API definitions available at the server's /docs URL. |
| License | The project says it is released under the bilibili Model Use License Agreement and asks users to read its disclaimer before use. | The model is released under the Apache 2.0 license. |
| Product | IndexTTS is a zero-shot text-to-speech system that clones a voice from a single reference audio clip. | MetaVoice-1B is an open-source foundational text-to-speech model. |
| Voice cloning | Yes | It supports zero-shot cloning of American and British voices from 30 seconds of reference audio. |