Update README.md
Browse files
README.md
CHANGED
|
@@ -25,6 +25,8 @@ For more information, check out the project page at https://mbzuai-oryx.github.i
|
|
| 25 |
<img src="assets/arch_diagram.svg" alt="LLMVoX Architecture" width="800px">
|
| 26 |
</p>
|
| 27 |
|
|
|
|
|
|
|
| 28 |
## Overview
|
| 29 |
|
| 30 |
LLMVoX is a lightweight 30M-parameter, LLM-agnostic, autoregressive streaming Text-to-Speech (TTS) system designed to convert text outputs from Large Language Models into high-fidelity streaming speech with low latency.
|
|
|
|
| 25 |
<img src="assets/arch_diagram.svg" alt="LLMVoX Architecture" width="800px">
|
| 26 |
</p>
|
| 27 |
|
| 28 |
+
<video src="https://github.com/user-attachments/assets/d670efd2-9c5a-4d7f-8c03-4af46baef91f" width="500" controls></video>
|
| 29 |
+
|
| 30 |
## Overview
|
| 31 |
|
| 32 |
LLMVoX is a lightweight 30M-parameter, LLM-agnostic, autoregressive streaming Text-to-Speech (TTS) system designed to convert text outputs from Large Language Models into high-fidelity streaming speech with low latency.
|