split into compose/auto, describe Auto, make consistent capitalization.

gudj0 · gudj0 · commit 839f4aaf5e5f · 2025-02-06T15:34:22.000+01:00
diff --git a/api-reference/WSDC_Migration_Guide.mdx b/api-reference/WSDC_Migration_Guide.mdx
@@ -23,7 +23,7 @@ It's simple, the datachannel worked horribly as a session init mechanism over tu
 
 ### Session Init
 
-Well, you had a POST call to `https://api.simli.ai/StartWebRTCSession` which you sent a JSON with `{sdp: pc.localDescription.sdp, type: pc.localDescription.type}`. Now, it's a WebSocket connection to `wss://api.simli.ai/StartWebRTCSession` to which you send the same JSON. On it, you receive two messages, the first one is reserved for possible future behavior, the second one is the output of the POST call: `{sdp:remoteSDP, type:"answer"}`. The second response you use with `pc.setRemoteDescrition(ANSWER_RECEIVED_FROM_WEBSOCKET)` and that's the main difference in session initiallization nothing more.
+Well, you had a POST call to `https://api.simli.ai/startWebRTCSession` which you sent a JSON with `{sdp: pc.localDescription.sdp, type: pc.localDescription.type}`. Now, it's a WebSocket connection to `wss://api.simli.ai/startWebRTCSession` to which you send the same JSON. On it, you receive two messages, the first one is reserved for possible future behavior, the second one is the output of the POST call: `{sdp:remoteSDP, type:"answer"}`. The second response you use with `pc.setRemoteDescrition(ANSWER_RECEIVED_FROM_WEBSOCKET)` and that's the main difference in session initiallization nothing more.
 
 ### Sending and Receiving Data
 
diff --git a/api-reference/endpoint/StartWebRTCSession.mdx b/api-reference/endpoint/StartWebRTCSession.mdx
@@ -1,5 +1,5 @@
 ---
-title: '/StartWebRTCSession'
+title: '/startWebRTCSession'
 description: 'Start a WebRTC session'
-openapi: 'POST /StartWebRTCSession'
+openapi: 'POST /startWebRTCSession'
 ---
diff --git a/api-reference/endpoint/customLLM.mdx b/api-reference/endpoint/customLLM.mdx
@@ -1,13 +1,13 @@
 ---
-title: "Use your own LLM"
+title: "Bring your own LLM"
 icon: comments
 ---
 
 TL;DR, If you have an OpenAI compatible API (test it out with the python or JS SDKs), pass [Simli the base url, an API key, and the model name](/api-reference/endpoint/startE2ESession#body-custom-llm-config-base-url) and you're golden!
 
 ## Background
 
-Using the Simli manged API is awesome! But it can be a bit difficult to tailor it out for your needs. You may have a custom knowledgebase, a RAG powered system, using your finetuned LLM that's the best doctor or tutor ever known to mankind that you self-host, or just want to use a model that we don't readily support. If that's you, hello, you're in the right place.
+Using Simli Auto (our end-to-end API) is awesome! But it can be a bit difficult to tailor it out for your needs. You may have a custom knowledge base, a RAG powered system, using your fine-tuned LLM that's the best doctor or tutor ever known to mankind that you self-host, or just want to use a model that we don't readily support. If that's you, you're in the right place.
 
 There's a fun trick that you may already know about if you're this deep into the weeds, if you look at the [Deepseek api docs](https://api-docs.deepseek.com/), you can see that they're using the OpenAI SDK as if it was their own! They just put in the base_url for their API and the API key and then it works as if nothing weird is going on.
 
diff --git a/api-reference/endpoint/startE2ESession.mdx b/api-reference/endpoint/startE2ESession.mdx
@@ -3,4 +3,8 @@ title: "/startE2ESession"
 openapi: "POST /startE2ESession"
 ---
 
+The Simli Auto API offers a quick and easy way to make an end-to-end real-time interaction. Simli Auto now supports [custom LLMs](api-reference/endpoint/customLLM), but if you need even more composability, check out the [Simli Compose API Reference](/api-reference/endpoint/textToVideoStream) instead.
+
+This endpoint allows you to start a new end-to-end session. 
+
 for changing the interaction languages, you can look at the support list on [Deepgram's website](https://developers.deepgram.com/docs/models-languages-overview)
diff --git a/api-reference/openapi.json b/api-reference/openapi.json
@@ -174,7 +174,7 @@
       }
     },
 
-    "/StartWebRTCSession": {
+    "/startWebRTCSession": {
       "post": {
         "summary": "Start WebRTC Session",
         "requestBody": {
diff --git a/api-reference/simli-agent.mdx b/api-reference/simli-agent.mdx
@@ -3,7 +3,7 @@ title: Create Simli Agent
 icon: github
 ---
 
-The easiest way to get started building with Simli is by using the Create Simli Agent repo. This allows you to get an agent interaction running in minutes, perfect for a proof-of-concept or simple web-app.
+The easiest way to get started building with Simli is by using the Create Simli Agent repo together with Simli Auto. This allows you to get an agent interaction running in minutes, perfect for a proof-of-concept or simple web-app.
 
 Important: This solution has limited composability, so if you are planning on building custom features or need to control your own LLM, you should use PipeCat instead.
 
diff --git a/api-reference/simli-webrtc.mdx b/api-reference/simli-webrtc.mdx
@@ -188,7 +188,7 @@ async function connectToRemotePeer() {
   var codec;
   document.getElementById("offer-sdp").textContent = offer.sdp;
 
-  const ws = new WebSocket("wss://api.simli.ai/StartWebRTCSession");
+  const ws = new WebSocket("wss://api.simli.ai/startWebRTCSession");
   wsConnection = ws;
   ws.addEventListener("open", () => {
     ws.send(
@@ -536,7 +536,7 @@ function connectToRemotePeer() {
   var codec;
   document.getElementById("offer-sdp").textContent = offer.sdp;
 
- const ws = new WebSocket("wss://api.simli.ai/StartWebRTCSession");
+ const ws = new WebSocket("wss://api.simli.ai/startWebRTCSession");
   wsConnection = ws;
   ws.addEventListener("open", () => {
     ws.send(
diff --git a/api-reference/webrtc-signaling-guide.mdx b/api-reference/webrtc-signaling-guide.mdx
@@ -4,7 +4,7 @@ title: 'WebRTC with WebSockets Signaling Guide'
 
 This endpoint is a websocket endpoint that takes in a stream of PCM16 audio frames and a set of control signals to manage a WebRTC Stream. The server sends only pongs, keepalive "ACK" messages, and a STOP signal when the server wants to terminate the session
 
-<Note>WebSocket URL: `wss://api.simli.ai/StartWebRTCSession`</Note>
+<Note>WebSocket URL: `wss://api.simli.ai/startWebRTCSession`</Note>
 
 ## Initial Request Format
 
diff --git a/get-started.mdx b/get-started.mdx
@@ -19,7 +19,7 @@ description: "Use our simli-client sdk to start streaming"
 Our API comprimises of two main components:
 
 - `/startAudioToVideoSession` API to initialize a session.
-- `/StartWebRTCSession` WebRTC API to start streaming `PCM16` audio bytes to video.
+- `/startWebRTCSession` WebRTC API to start streaming `PCM16` audio bytes to video.
 
 If you're a WebRTC enthusiast, we encourage you to learn more about [Simli WebRTC](/api-reference/simli-webrtc)
 
diff --git a/introduction.mdx b/introduction.mdx
@@ -14,22 +14,22 @@ Clone a starter repo to get started in minutes
   icon="github"
   href="https://github.com/simliai/create-simli-agent"
 >
-The quickest way to get started building with Simli is by using the Create Simli Agent repo. This allows you to get a basic agent interaction running in minutes, perfect for a proof-of-concept or simple web-app.
+The quickest way to get started building with Simli is by using the Create Simli Agent repo together with Simli Auto. This allows you to get a basic agent interaction running in minutes, perfect for a proof-of-concept or simple web-app.
 </Card>
 <Card
   title="Pipecat"
   icon="github"
   href="https://github.com/pipecat-ai/pipecat"
 >
-We recommend using Pipecat's starter repo if you want more composability and customization, for example if you need to bring your own LLM. 
+We recommend using Pipecat if you want more composability and customization, for example if you need to bring your own LLM. 
 </Card>
 
 <Card
   title="create-simli-app"
   icon="github"
   href="https://github.com/simliai/create-simli-app-openai"
 >
-  This repo is a simple Next.JS app that uses Simli with OpenAI real-time conversations, but you can swap it out with any other voice provider you'd like!
+  This repo is a simple Next.JS app that uses Simli Compose with OpenAI real-time conversations, but you can swap it out with any other voice provider you'd like!
 </Card>
 
 ## An API with endless possibilities.
diff --git a/mint.json b/mint.json
@@ -53,20 +53,20 @@
       ]
     },
     {
-      "group": "Video API Reference",
+      "group": "Simli Compose - API Reference",
       "pages": [
         "api-reference/endpoint/textToVideoStream",
         "api-reference/endpoint/audioToVideoStream",
         "api-reference/endpoint/startAudioToVideoSession",
-        "api-reference/endpoint/StartWebRTCSession",
-        "api-reference/endpoint/getIceServers",
-        {
-          "group": "End 2 End API (Simli Auto)",
-          "pages": [
-            "api-reference/endpoint/startE2ESession",
-            "api-reference/endpoint/customLLM"
-          ]
-        }
+        "api-reference/endpoint/startWebRTCSession",
+        "api-reference/endpoint/getIceServers"
+      ]
+    },
+    {
+      "group": "Simli Auto - API Reference",
+      "pages": [
+        "api-reference/endpoint/startE2ESession",
+        "api-reference/endpoint/customLLM"
       ]
     },
     {
@@ -78,11 +78,13 @@
     },
     {
       "group": "",
-      "pages": ["api-reference/discord"]
+      "pages": [
+        "api-reference/discord"
+      ]
     }
   ],
   "modeToggle": {
     "default": "dark",
     "isHidden": true
   }
-}
+}

Original file line number	Diff line number	Diff line change
`@@ -174,7 +174,7 @@`
`174`	`174`	`}`
`175`	`175`	`},`
`176`	`176`
`177`		`- "/StartWebRTCSession": {`
	`177`	`+ "/startWebRTCSession": {`
`178`	`178`	`"post": {`
`179`	`179`	`"summary": "Start WebRTC Session",`
`180`	`180`	`"requestBody": {`