Update README.md

README.md

@@ -35,14 +35,21 @@ extra_gated_description: >-
 pipeline_tag: audio-text-to-text
 ---
 
-# Voxtral-Small-24B-2507
+# Voxtral Small 24B-2507
 
-Voxtral-Small-24B-2507 is our first Audio model, built upon Small 3, it has audio and text input capabilities, its designed for tasks such as dialog understanding, transcriptions, and speech to text tasks.
+Voxtral Small is an enhancement of [Mistral Small 3](https://huggingface.co/mistralai/Mistral-Small-24B-Base-2501), incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription and understanding.
 
-Learn more about Voxtral in our blog post [here](#).
+Learn more about Voxtral in our blog post [here](https://mistral.ai/news/voxtral-2507).
 
 ## Key Features
 
+Voxtral builds upon Mistral Small 3 with powerful audio understanding capabilities.
+- Audio and text understanding
+- **32k context length** for more than **30 minutes of audio**
+- Audio understanding for **transcriptions**, **summaries**, **translations**, and much more
+- Segment granularity timestamping
+- Function Calling
+
 ## Benchmark Results
 
 ### Audio