Update README.md

README.md

@@ -198,7 +198,7 @@ print(content)
 
 #### Transcription
 
-Voxtral-Small-24B-2507 has powerful transcription capabilities! 
+Voxtral-Small-24B-2507 has powerful transcription capabilities! These are enabled by creating a dedicated `TranscriptionRequest`, which triggers the model's "transcription-mode".
 
 Make sure that your client has `mistral-common` with audio installed:
 
@@ -209,6 +209,8 @@ pip install --upgrade mistral_common\[audio\]
 <details>
   <summary>Python snippet</summary>
 
+Setting `language="en"` disables automatic language detection and assumes transcription in the specified language (e.g. English in this example). For automatic language detection, set `language=None`.
+
 ```python
 from mistral_common.protocol.transcription.request import TranscriptionRequest
 from mistral_common.protocol.instruct.messages import RawAudio