docs(FEA-2094): sync add-on statuses and deprecate chapterization

api-reference/v2/live/callback/post-chapterization.mdx

@@ -1,5 +1,5 @@
 ---
-title: Chapterization
-description: Payload definition for the callback event `live.post_chapterization`.
+title: Chapterization (deprecated)
+description: "**[Deprecated]** Chapterization no longer returns results. Use Audio-to-LLM on pre-recorded transcription instead."
 openapi-schema: CallbackLivePostChapterizationMessage
----
+---

api-reference/v2/live/message/post-chapterization.mdx

@@ -1,5 +1,5 @@
 ---
-title: Chapterization
-description: Payload definition for the message `post_chapterization`.
+title: Chapterization (deprecated)
+description: "**[Deprecated]** Chapterization no longer returns results. Use Audio-to-LLM on pre-recorded transcription instead."
 openapi-schema: PostChapterizationMessage
----
+---

asyncapi.yaml

@@ -298,9 +298,9 @@ components:
         $ref: "#/components/schemas/PostFinalTranscriptMessage"
     postChapterization:
       name: post_chapterization
-      title: Chapterization
+      title: Chapterization (deprecated)
       contentType: application/json
-      summary: This message contains the informations about the post chapterization of the audio chunk.
+      summary: "**[Deprecated]** Chapterization no longer returns results. Use audio_to_llm on pre-recorded transcription instead; Audio-to-LLM is more powerful and fully customizable via custom prompts."
       payload:
         $ref: "#/components/schemas/PostChapterizationMessage"
     postSummarization:
@@ -905,6 +905,8 @@ components:
                     - { $ref: "#/components/schemas/ErrorObject" }
                 results: { type: string }
             chapterization:
+              deprecated: true
+              description: "**[Deprecated]** Chapterization no longer returns results. Use audio_to_llm on pre-recorded transcription instead; Audio-to-LLM is more powerful and fully customizable via custom prompts."
               type: object
               properties:
                 success: { type: boolean }
@@ -931,6 +933,8 @@ components:
 
     PostChapterizationMessage:
       type: object
+      deprecated: true
+      description: "**[Deprecated]** Chapterization no longer returns results. Use audio_to_llm on pre-recorded transcription instead; Audio-to-LLM is more powerful and fully customizable via custom prompts."
       required: [session_id, created_at, type, data]
       properties:
         session_id: { $ref: "#/components/schemas/UUID" }

chapters/audio-intelligence/audio-to-llm.mdx

@@ -9,12 +9,12 @@
 
 **Audio-to-LLM** runs once the transcription is generated. You provide **one or more prompts**; each prompt is executed against the **transcript text** from the same job using the configured model, yielding **one LLM response per prompt**. Use it to extract action items, answer questions about the recording, or run any text analysis you express in natural language.
 
-Unlike the built-in [Summarization](/chapters/audio-intelligence/summarization) feature — which produces a fixed-format summary — Audio-to-LLM lets you write **your own instructions**: ask for a summary in the exact format, tone, and level of detail your product needs, or combine a summary with other analyses (action items, compliance checks) in a single request.
+Unlike the built-in [Summarization](/chapters/audio-intelligence/summarization) feature, which produces a fixed-format summary, Audio-to-LLM lets you write **your own instructions**: ask for a summary in the exact format, tone, and level of detail your product needs, or combine a summary with other analyses (action items, compliance checks) in a single request. It also replaces the deprecated [Chapterization](/chapters/audio-intelligence/chapterization) add-on for chapter-style structuring of long audio, with full control over format and content via custom prompts.
 
 ## Usage
 
 1. Include `audio_to_llm: true` and an `audio_to_llm_config` object (at minimum, a `prompts` array) in your [pre-recorded transcription request](/chapters/pre-recorded-stt/quickstart).
 2. Gladia transcribes the audio, along with any other audio-intelligence options you enabled on that request.
 3. Each prompt is run on the resulting transcript via the LLM.
 4. The API returns **one result object per prompt** (same order as `prompts`), each containing the original `prompt` and the model `response`.
 
@@ -26,7 +26,7 @@
 
 By default the model used to execute your prompts is **[GPT 5.4 Nano](https://openrouter.ai/openai/gpt-5.4-nano)** (`openai/gpt-5.4-nano`), a fast option suited to high-volume summaries and extraction. The `model` can be customized when you need stronger reasoning, richer analysis, longer outputs, or behavior that fits a specific model.
 
 You can use **any model listed on [OpenRouter](https://openrouter.ai/models)** by setting the `model` key. Prices reflect the public OpenRouter rate plus a platform fee added by Gladia.
 
 ## Example
 

chapters/audio-intelligence/chapterization.mdx

@@ -1,95 +1,18 @@
 ---
 title: "Chapterization"
-description: "The Chapterization model segments the audio into distinct chapters, each with a descriptive headline and summaries"
+description: "Chapterization is deprecated and no longer returns results. Use Audio-to-LLM for customizable chapter-style structuring of long audio."
 ---
 
 import PrerecordedBadge from "/snippets/badges/prerecorded.mdx"
 import LiveBadge from "/snippets/badges/live.mdx"
 
 <PrerecordedBadge />
 <LiveBadge />
-<Note>
-This feature is in **Alpha** state.<br/>
-Breaking changes may still be introduced to this API, but advance notice will be sent.
 
-We're looking for feedback to improve this feature, [share yours on Discord](https://discord.gg/T22a4ETUQp).
+<Warning>
+This feature is **deprecated** and **no longer returns results**.
 
-</Note>
-The chapterization model segments the audio 
-into logical chapters based on the audio and content, and makes it easier to navigate long audios such as meeting recordings.
+Use [Audio-to-LLM](/chapters/audio-intelligence/audio-to-llm) instead. It is more powerful and fully customizable: you write your own prompts to segment long audio, generate headlines and summaries, or structure the transcript however your product needs.
+</Warning>
 
-Each chapter will contain its start and end time, as well as a summary, headline, bottom line "gist" and keywords.
-
-## Usage
-
-Enable chapterization by setting the appropriate flag:
-
-<CodeGroup>
-```json Pre-recorded
-{
-  "chapterization": true
-}
-```
-```json Live
-{
-  "post_processing": {
-    "chapterization": true
-  },
-  "messages_config": {
-    "receive_post_processing_events": true
-  }
-}
-```
-</CodeGroup>
-## Result
-The transcription result will contain a `"chapterization"` key with the output of the model:
-
-<CodeGroup>
-```json Pre-recorded
-{
-  "transcription":{...},
-  "chapterization": {
-    "success": true,
-    "is_empty": false,
-    "results": [
-          {
-            "summary": "In a world where minimalism is valued, yet excess is desired, hope for the future remains. The past predicts the present, which is yet to be determined.",
-            "headline": "Headline: \"Embracing Hope: The Interconnectedness of Past, Present, and Future\"",
-            "gist": "Embracing Hope: Past, Present, Future Interconnected",
-            "keywords": [
-              "Split infinity",
-              "less is more",
-              "too much",
-              "hope",
-              "present"
-            ],
-            "start": 0.0,
-            "end": 19.83977,
-        }],
-    "exec_time": 5.078396797180176,
-    "error": null
-  }
-}
-```
-```json Live
-{
-  "session_id": "550e8400-e29b-41d4-a716-446655440000",
-  "created_at": "2025-09-19T12:46:00Z",
-  "type": "post_chapterization",
-  "error": null,
-  "data": {
-    "results": [
-      {
-        "headline": "Project kickoff",
-        "start": 0,
-        "end": 60,
-        "keywords": [
-          "timeline",
-          "owner"
-        ]
-      }
-    ]
-  }
-}
-```
-</CodeGroup>
+The `chapterization` parameter remains in the API for backward compatibility, but enabling it will not produce chapter results. New integrations should use Audio-to-LLM.

chapters/audio-intelligence/index.mdx

@@ -1,9 +1,9 @@
 ---
 title: Audio Intelligence
-description: "Turn speech into actionable insights with translation, summarization, entities, chapters, sentiment and more"
+description: "Turn speech into actionable insights with translation, summarization, entities, sentiment, custom LLM prompts and more"
 ---
 
-Audio intelligence turns raw speech into structured, useful data on top of transcription. Once the words are captured, these features help you understand, organize, and act on the content — from instant translation to key-point summaries, entity detection, chapter markers, emotions, and even custom LLM prompts.
+Audio intelligence turns raw speech into structured, useful data on top of transcription. Once the words are captured, these features help you understand, organize, and act on the content: from instant translation to key-point summaries, entity detection, emotions, and custom LLM prompts.
 
 Use these capabilities alongside Live or Pre-recorded STT to automate workflows like meeting notes, voice agents, compliance redaction, knowledge extraction, and multilingual publishing.
 
@@ -53,7 +53,7 @@ Use these capabilities alongside Live or Pre-recorded STT to automate workflows
     icon="bookmark"
     href="/chapters/audio-intelligence/chapterization"
   >
-    Segment long audio into chapters with headlines and summaries for easy navigation.
+    Deprecated. Prefer Audio-to-LLM for customizable chapter-style structuring of long audio.
   </Card>
 
   <Card

chapters/audio-intelligence/named-entity-recognition.mdx

@@ -10,7 +10,7 @@
 <LiveBadge />
 
 <Note>
-This feature is in **Alpha** state.<br/>
+This feature is in **Beta** state.<br/>
 Breaking changes may still be introduced to this API, but an advanced notice will be sent.
 
 We're looking for feedback to improve this feature, [share yours on Discord](https://discord.gg/T22a4ETUQp).
@@ -26,7 +26,7 @@
 <CodeGroup>
 ```json Pre-recorded
 {
   "named_entity_recognition": true
 }
 ```
 ```json Live
@@ -61,7 +61,7 @@
         "entity_type": "AGE",
         "text": "27 years old",
         "start": 234.7,
         "end": 235.6
       }
     ],
     "exec_time": 1.7726809978485107,