Add support for text to speech in chat responses (#821)

* Enable speech to text responses in khoj chat

- Current issue: reads out all the markdown formatting, plus waits for the whole result to be streamed before playing it

* Extract content from markdown-formatted text

* Add a loader for while you're waiting for Khoj's response

* Add user configuration option for chat model options, allow server side configuration for option list

* Join up APIs, views, admin pages to allow configuring custom voice models

src/khoj/database/models/__init__.py

@@ -97,6 +97,11 @@ class ChatModelOptions(BaseModel):
     )
 
 
+class VoiceModelOption(BaseModel):
+    model_id = models.CharField(max_length=200)
+    name = models.CharField(max_length=200)
+
+
 class Agent(BaseModel):
     creator = models.ForeignKey(
         KhojUser, on_delete=models.CASCADE, default=None, null=True, blank=True
@@ -248,6 +253,11 @@ class UserConversationConfig(BaseModel):
     setting = models.ForeignKey(ChatModelOptions, on_delete=models.CASCADE, default=None, null=True, blank=True)
 
 
+class UserVoiceModelConfig(BaseModel):
+    user = models.OneToOneField(KhojUser, on_delete=models.CASCADE)
+    setting = models.ForeignKey(VoiceModelOption, on_delete=models.CASCADE, default=None, null=True, blank=True)
+
+
 class UserSearchModelConfig(BaseModel):
     user = models.OneToOneField(KhojUser, on_delete=models.CASCADE)
     setting = models.ForeignKey(SearchModelConfig, on_delete=models.CASCADE)