Skip to content

Open-source State-of-the-art TTS model which runs on a CPU 😻

Python

Update api.md

Kittene948cb2fb163
diff --git a/docs/api.md b/docs/api.md
index 7c5748d..f0f6009 100644
--- a/docs/api.md
+++ b/docs/api.md
@@ -10,7 +10,7 @@ Loads whichever model family the repository's `config.json` declares.
|---|---|---|---|
| `model_name` | `str` | -- | Hugging Face repo ID, or a path to a local repository directory |
| `cache_dir` | `str` | `None` | Local directory for caching downloaded files |
-| `device` | `str` | `None` | `"cuda"` or `"cpu"`; auto-detected when omitted. Note: this Python package is for demo only, and not optimized for speed. For real-time performance on CPU, please refer to our [optimized implementation](https://github.com/KittenML/KittenTTS#running-on-cpu). And for GPU, please refer to the vllm instructions below. |
+| `device` | `str` | `None` | `"cuda"` or `"cpu"`; auto-detected when omitted. Note: this Python package is for demo only, and not optimized for speed. For real-time performance on CPU, please refer to our [optimized cpu inference repo](https://github.com/KittenML/kitten-tts-2-cpp). And for GPU, please refer to the vllm instructions below. |
| `hf_token` | `str` | `None` | Token, only for downloading a private model repository |
| `decoder` | `str` | repo default | Which decoder to load; see [decoders.md](decoders.md) |
| `weights` | `str` | `"packed"` | Which weight packing to load: `"packed"` (lossless), `"emb4"` (smaller, quantised embedding), `"full"` (bf16) |