docs: add studio screenshot to README
Browse files- README.md +2 -0
- docs/samples/studio-clone.png +3 -0
README.md
CHANGED
|
@@ -15,6 +15,8 @@ short_description: Cloning, preset voices, voice design & LoRA — Qwen3-TTS
|
|
| 15 |
|
| 16 |
The open-source voice studio for **Qwen3-TTS-12Hz-1.7B** — voice cloning, 9 premium preset voices with emotion control, and text-described voice design, in one Gradio app. **Fidelity first.** Runs natively on Apple silicon (MPS) and deploys to Hugging Face ZeroGPU.
|
| 17 |
|
|
|
|
|
|
|
| 18 |
## Features
|
| 19 |
- **3-second voice cloning** — reference audio + transcript, or x-vector-only *(Base)*
|
| 20 |
- **9 preset voices** incl. Beijing/Sichuan dialects, with natural-language emotion/style instructions *(CustomVoice)*
|
|
|
|
| 15 |
|
| 16 |
The open-source voice studio for **Qwen3-TTS-12Hz-1.7B** — voice cloning, 9 premium preset voices with emotion control, and text-described voice design, in one Gradio app. **Fidelity first.** Runs natively on Apple silicon (MPS) and deploys to Hugging Face ZeroGPU.
|
| 17 |
|
| 18 |
+
|
| 19 |
+
|
| 20 |
## Features
|
| 21 |
- **3-second voice cloning** — reference audio + transcript, or x-vector-only *(Base)*
|
| 22 |
- **9 preset voices** incl. Beijing/Sichuan dialects, with natural-language emotion/style instructions *(CustomVoice)*
|
docs/samples/studio-clone.png
ADDED
|
Git LFS Details
|