Skip to content

Open-Source Frontier Voice AI

Python

update

YaoyaoChang7ea24a4fb976
diff --git a/README.md b/README.md
index 2517e0f..64033a4 100644
--- a/README.md
+++ b/README.md
@@ -23,7 +23,7 @@
<img src="https://img.shields.io/badge/Status-New-brightgreen?style=flat" alt="New" />
<img src="https://img.shields.io/badge/Feature-Realtime_TTS-blue?style=flat&logo=soundcharts" alt="Realtime TTS" />
-<strong>2025-12-03: 📣 We open-sourced <a href="docs/vibevoice-realtime-0.5b.md"><strong>VibeVoice‑Realtime‑0.5B</strong></a>, a real‑time text‑to‑speech model that supports streaming text input and robust long-form speech generation.</strong>
+<strong>2025-12-03: 📣 We open-sourced <a href="docs/vibevoice-realtime-0.5b.md"><strong>VibeVoice‑Realtime‑0.5B</strong></a>, a real‑time text‑to‑speech model that supports streaming text input and robust long-form speech generation. Try it on [Colab](https://colab.research.google.com/github/microsoft/VibeVoice/blob/main/demo/vibevoice_realtime_colab.ipynb).</strong>
<br>
https://github.com/user-attachments/assets/0901d274-f6ae-46ef-a0fd-3c4fba4f76dc
diff --git a/demo/web/index.html b/demo/web/index.html
index feb9673..daf9df8 100644
--- a/demo/web/index.html
+++ b/demo/web/index.html
@@ -351,12 +351,12 @@
<div class="control-row">
<label class="range-control">
<span>CFG</span>
- <input id="cfgScale" type="range" min="1" max="3" step="0.05" value="1.5" />
+ <input id="cfgScale" type="range" min="1.3" max="3" step="0.05" value="1.5" />
<span class="range-value" id="cfgValue">1.5</span>
</label>
<label class="range-control">
<span>Inference Steps</span>
- <input id="inferenceSteps" type="range" min="1" max="20" step="1" value="5" />
+ <input id="inferenceSteps" type="range" min="5" max="20" step="1" value="5" />
<span class="range-value" id="stepsValue">5</span>
</label>
<button id="resetControls" type="button" class="secondary-btn">Reset Controls</button>
@@ -482,7 +482,7 @@
};
const updateCfgDisplay = () => {
- cfgValueLabel.textContent = Number(cfgSelect.value).toFixed(3);
+ cfgValueLabel.textContent = Number(cfgSelect.value).toFixed(2);
};
const updateStepsDisplay = () => {
diff --git a/docs/vibevoice-realtime-0.5b.md b/docs/vibevoice-realtime-0.5b.md
index 096b2ec..2b412c8 100644
--- a/docs/vibevoice-realtime-0.5b.md
+++ b/docs/vibevoice-realtime-0.5b.md
@@ -111,11 +111,11 @@ Due to network latency, the time when audio playback is heard may exceed the ~30
python demo/vibevoice_realtime_demo.py --model_path microsoft/VibeVoice-Realtime-0.5B
```
-Tip: You can also deploy and run the real-time demo on [Colab](https://colab.research.google.com/github/microsoft/VibeVoice/blob/main/demo/vibevoice_realtime_colab.ipynb).
+Tip: Just try it on [Colab](https://colab.research.google.com/github/microsoft/VibeVoice/blob/main/demo/vibevoice_realtime_colab.ipynb).
### Usage 2: Inference from files directly
```bash
-# We provide some LLM generated example scripts under demo/text_examples/ for demo
+# We provide some example scripts under demo/text_examples/ for demo
python demo/realtime_model_inference_from_file.py --model_path microsoft/VibeVoice-Realtime-0.5B --txt_path demo/text_examples/1p_vibevoice.txt --speaker_name Carter
```