documentation update

Author: mkopcins

docs/docs/03-hooks/01-natural-language-processing/useLLM.md

@@ -494,13 +494,13 @@ Depending on selected model and the user's device generation speed can be above
 
 ## Vision-Language Models (VLM)
 
-Some models support multimodal input — text and images together. To use them, pass a `capabilities` array when loading the model.
+Some models support multimodal input — text, images and/or audio together. To use them, pass a `capabilities` array when loading the model.
 
 ### Loading a VLM
 
 ```tsx
 import { models, useLLM } from 'react-native-executorch';
-const llm = useLLM({ model: models.llm.lfm2_5_vl_1_6b() });
+const llm = useLLM({ model: models.llm.gemma4_e2b_multimodal() });
 ```
 
 The `capabilities` field is already set on the model constant. You can also construct the model object explicitly:
@@ -511,22 +511,26 @@ const llm = useLLM({
     modelSource: '...',
     tokenizerSource: '...',
     tokenizerConfigSource: '...',
-    capabilities: ['vision'],
+    capabilities: ['vision', 'audio'],
   },
 });
 ```
 
 Passing `capabilities` unlocks the typed `media` argument on `sendMessage`.
 
-### Sending a message with an image
+### Sending a message with an image or audio recording
 
 ```tsx
-const llm = useLLM({ model: models.llm.lfm2_5_vl_1_6b() });
+const llm = useLLM({ model: models.llm.gemma4_e2b_multimodal() });
 
 const send = () => {
   llm.sendMessage('What is in this image?', {
     imagePath: '/path/to/image.jpg',
   });
+  // or
+  llm.sendMessage('What can you hear?', {
+    audioBuffer: audioRecording,
+  });
 };
 
 return (
@@ -538,6 +542,7 @@ return (
 ```
 
 The `imagePath` should be a local file path on the device.
+The `audioBuffer` should be a `Float32Array` with 16kHz waveform.
 
 ### Functional generation with images
 

docs/docs/04-typescript-api/01-natural-language-processing/LLMModule.md

@@ -118,12 +118,12 @@ Model presets expose an optional `generationConfig` that `LLMModule.fromModelNam
 
 ## Vision-Language Models (VLM)
 
-Some models support multimodal input — text and images together. To use them, pass `capabilities` in the model object when calling [`fromModelName`](../../06-api-reference/classes/LLMModule.md#frommodelname):
+Some models support multimodal input — text, images and/or audio together. To use them, pass `capabilities` in the model object when calling [`fromModelName`](../../06-api-reference/classes/LLMModule.md#frommodelname):
 
 ```typescript
 import { models, LLMModule } from 'react-native-executorch';
 const llm = await LLMModule.fromModelName(
-  models.llm.lfm2_5_vl_1_6b(),
+  models.llm.gemma4_e2b_multimodal(),
   undefined,
   (token) => console.log(token)
 );
@@ -133,20 +133,24 @@ The `capabilities` field is already set on the model constant. You can also cons
 
 ```typescript
 const llm = await LLMModule.fromModelName({
-  modelName: 'lfm2.5-vl-1.6b-quantized',
+  modelName: 'gemma4-e2b-multimodal',
   modelSource: require('./path/to/model.pte'),
   tokenizerSource: require('./path/to/tokenizer.json'),
   tokenizerConfigSource: require('./path/to/tokenizer_config.json'),
-  capabilities: ['vision'],
+  capabilities: ['vision', 'audio'],
 });
 ```
 
-Once loaded, pass `imagePath` to [`sendMessage`](../../06-api-reference/classes/LLMModule.md#sendmessage):
+Once loaded, pass `imagePath`Once loaded, pass `imagePath` or `audioBuffer` to [`sendMessage`](../../06-api-reference/classes/LLMModule.md#sendmessage):
 
 ```typescript
 const response = await llm.sendMessage('What is in this image?', {
   imagePath: '/path/to/image.jpg',
 });
+// or
+const response = await llm.sendMessage('What can you hear?', {
+  audioBuffer: audioRecording, //expected as waveform 16kHz
+});
 ```
 
 Or use [`generate`](../../06-api-reference/classes/LLMModule.md#generate) with `mediaPath` on the message:
@@ -159,7 +163,14 @@ const chat: Message[] = [
     mediaPath: '/path/to/image.jpg',
   },
 ];
-
+// or
+const chat: Message[] = [
+  {
+    role: 'user',
+    content: 'Transcribe the recording.',
+    audioWaveform: audioRecording,
+  },
+];
 const response = await llm.generate(chat);
 ```