chores: lemur purge + api spec changes (#476)

m-ods · a-dinoto · web-flow · commit 7c6f9065ac59 · 2025-11-05T04:37:28.000-05:00
* remove references to lemur

* update api specs with new streaming parameters

* fix: minor edits

* hide page link istead of delete

* hide link instead of delete

---------

Co-authored-by: Amanda DiNoto &lt;adinoto@assemblyai.com&gt;
diff --git a/fern/cookbooks/core-transcription/migration_guides/oai_to_aai.mdx b/fern/cookbooks/core-transcription/migration_guides/oai_to_aai.mdx
@@ -73,4 +73,4 @@ Key differences:
 - With AssemblyAI, timestamp granularity is word-level by default
 - The results for Speaker Diarization are stored in `transcript.utterances`. To see the full transcript response object, refer to our [API Reference](https://www.assemblyai.com/docs/api-reference).
 - Check our [documentation](https://www.assemblyai.com/docs/audio-intelligence) for our full list of available features and their parameters
-- If you want to send a custom prompt to the LLM, you can use [LeMUR Task](https://www.assemblyai.com/docs/lemur/examples) and apply the model to your transcribed audio files.
+- If you want to send a custom prompt to an LLM, you can use [LLM Gateway](/docs/llm-gateway/overview) to apply the model to your transcribed audio files.
diff --git a/fern/cookbooks/core-transcription/schedule_delete.mdx b/fern/cookbooks/core-transcription/schedule_delete.mdx
@@ -23,7 +23,7 @@ AAI_API_TOKEN = ""
 
 **Make sure not to share this token with anyone** - it is a private key associated uniquely to your account.
 
-Next, we'll install the AssemblyAI Python SDK, which will allow us to easily use LeMUR in just a few lines of code.
+Next, we'll install the AssemblyAI Python SDK.
 
 ```python
 !pip install "assemblyai"
diff --git a/fern/docs.yml b/fern/docs.yml
@@ -550,8 +550,8 @@ navigation:
               - section: Automatic Language Detection
                 skip-slug: true
                 contents:
-                  - page: Automatic Language Detection Workflow
-                    path: pages/05-guides/automatic-language-detection-workflow.mdx
+                  # - page: Automatic Language Detection Workflow
+                  #   path: pages/05-guides/automatic-language-detection-workflow.mdx
                   - page: Use Automatic Language Detection as a Separate Step From Transcription
                     path: pages/05-guides/cookbooks/core-transcription/automatic-language-detection-separate.mdx
                     slug: automatic-language-detection-separate
@@ -758,6 +758,7 @@ navigation:
                   - page: Generate Transcript Citations using LLM Gateway
                     path: pages/05-guides/cookbooks/lemur/lemur-transcript-citations.mdx
                     slug: lemur-transcript-citations
+                    hidden: true
               - section: Substitute Audio Intelligence with LLM Gateway
                 skip-slug: true
                 contents:
diff --git a/fern/pages/01-getting-started/transcribe-an-audio-file.mdx b/fern/pages/01-getting-started/transcribe-an-audio-file.mdx
@@ -957,7 +957,7 @@ Want to learn more?
 
 - For more ways to analyze your audio data, explore our [Audio Intelligence models](/audio-intelligence).
 - If you want to transcribe audio in real-time, see [Transcribe streaming audio from a microphone](/getting-started/transcribe-streaming-audio).
-- To search, summarize, and ask questions on your transcripts with LLMs, see [LeMUR](/lemur).
+- To search, summarize, and ask questions on your transcripts with LLMs, see [LLM Gateway](/docs/llm-gateway/overview).
 
 ## Need some help?
 
diff --git a/fern/pages/01-getting-started/transcribe-an-audio-file/csharp.mdx b/fern/pages/01-getting-started/transcribe-an-audio-file/csharp.mdx
@@ -379,7 +379,7 @@ Want to learn more?
 
 - For more ways to analyze your audio data, explore our [Audio Intelligence models](/audio-intelligence).
 - If you want to transcribe audio in real-time, see [Transcribe streaming audio from a microphone](/getting-started/transcribe-streaming-audio).
-- To search, summarize, and ask questions on your transcripts with LLMs, see [LeMUR](/lemur).
+- To search, summarize, and ask questions on your transcripts with LLMs, see [LLM Gateway](/docs/llm-gateway/overview).
 
 ## Need some help?
 
diff --git a/fern/pages/01-getting-started/transcribe-an-audio-file/javascript.mdx b/fern/pages/01-getting-started/transcribe-an-audio-file/javascript.mdx
@@ -140,8 +140,9 @@ transcribe();
 ## Before you begin
 
 To complete this tutorial, you need <a href="https://www.assemblyai.com/dashboard/signup" target="_blank">
-    {" "}
-    a free AssemblyAI account
+{" "}
+a free AssemblyAI account
+
   </a>
   .
 
@@ -521,7 +522,7 @@ Want to learn more?
 
 - For more ways to analyze your audio data, explore our [Audio Intelligence models](/audio-intelligence).
 - If you want to transcribe audio in real-time, see [Transcribe streaming audio from a microphone](/getting-started/transcribe-streaming-audio).
-- To search, summarize, and ask questions on your transcripts with LLMs, see [LeMUR](/lemur).
+- To search, summarize, and ask questions on your transcripts with LLMs, see [LLM Gateway](/docs/llm-gateway/overview).
 
 ## Need some help?
 
diff --git a/fern/pages/01-getting-started/transcribe-an-audio-file/php.mdx b/fern/pages/01-getting-started/transcribe-an-audio-file/php.mdx
@@ -335,7 +335,7 @@ Want to learn more?
 
 - For more ways to analyze your audio data, explore our [Audio Intelligence models](/audio-intelligence).
 - If you want to transcribe audio in real-time, see [Transcribe streaming audio from a microphone](/getting-started/transcribe-streaming-audio).
-- To search, summarize, and ask questions on your transcripts with LLMs, see [LeMUR](/lemur).
+- To search, summarize, and ask questions on your transcripts with LLMs, see [LLM Gateway](/docs/llm-gateway/overview).
 
 ## Need some help?
 
diff --git a/fern/pages/01-getting-started/transcribe-an-audio-file/python.mdx b/fern/pages/01-getting-started/transcribe-an-audio-file/python.mdx
@@ -462,7 +462,7 @@ Want to learn more?
 
 - For more ways to analyze your audio data, explore our [Audio Intelligence models](/audio-intelligence).
 - If you want to transcribe audio in real-time, see [Transcribe streaming audio from a microphone](/getting-started/transcribe-streaming-audio).
-- To search, summarize, and ask questions on your transcripts with LLMs, see [LeMUR](/lemur).
+- To search, summarize, and ask questions on your transcripts with LLMs, see [LLM Gateway](/docs/llm-gateway/overview).
 
 ## Need some help?
 
diff --git a/fern/pages/01-getting-started/transcribe-an-audio-file/ruby.mdx b/fern/pages/01-getting-started/transcribe-an-audio-file/ruby.mdx
@@ -324,7 +324,7 @@ Want to learn more?
 
 - For more ways to analyze your audio data, explore our [Audio Intelligence models](/audio-intelligence).
 - If you want to transcribe audio in real-time, see [Transcribe streaming audio from a microphone](/getting-started/transcribe-streaming-audio).
-- To search, summarize, and ask questions on your transcripts with LLMs, see [LeMUR](/lemur).
+- To search, summarize, and ask questions on your transcripts with LLMs, see [LLM Gateway](/docs/llm-gateway/overview).
 
 ## Need some help?
 
diff --git a/fern/pages/01-getting-started/transcribe-an-audio-file2.mdx b/fern/pages/01-getting-started/transcribe-an-audio-file2.mdx
@@ -106,7 +106,7 @@ const client = new AssemblyAI({
 const audioFile = "https://assembly.ai/sports_injuries.mp3";
 
 const params = {
-  audio: audioFile
+  audio: audioFile,
 };
 
 const run = async () => {
@@ -157,7 +157,7 @@ async function transcribe() {
          */
 
     const data = {
-      audio_url: audioFile // For local files use: audio_url: uploadUrl
+      audio_url: audioFile, // For local files use: audio_url: uploadUrl
     };
 
     const url = `${baseUrl}/v2/transcript`;
@@ -204,7 +204,9 @@ transcribe();
 To complete this tutorial, you need:
 
 - If opting to use the Python or Python SDK code, you will need [Python](https://www.python.org/) installed.
-- <a href="https://www.assemblyai.com/dashboard/signup" target="_blank">A free AssemblyAI account.</a>
+- <a href="https://www.assemblyai.com/dashboard/signup" target="_blank">
+    A free AssemblyAI account.
+  </a>
 
 ## Step 1: Install the necessary libraries
 
@@ -779,7 +781,7 @@ Want to learn more?
 
 - For more ways to analyze your audio data, explore our [Audio Intelligence models](/audio-intelligence).
 - If you want to transcribe audio in real-time, see [Transcribe streaming audio from a microphone](/getting-started/transcribe-streaming-audio).
-- To search, summarize, and ask questions on your transcripts with LLMs, see [LeMUR](/lemur).
+- To search, summarize, and ask questions on your transcripts with LLMs, see [LLM Gateway](/docs/llm-gateway/overview).
 
 ## Need some help?
 
diff --git a/fern/pages/02-speech-to-text/pre-recorded-audio/code-switching-docs.mdx b/fern/pages/02-speech-to-text/pre-recorded-audio/code-switching-docs.mdx
@@ -26,8 +26,8 @@ While additional languages are supported for code switching, optimal results typ
 We highly recommend testing sample code switching files with your specific audio to assess performance and evaluate outputs. We also recommend using an LLM to correct and fine-tune our model's outputs.
 
 ## Manually Setting Language Codes
- 
- To manually set the [language codes](/docs/speech-to-text/pre-recorded-audio/code-switching), you can use the `language_codes` parameter. A max of two language codes can be set and one code must be `"en"`. For example, if your file contains both English and Spanish, it would be `"language_codes": ["en", "es"]`.
+
+To manually set the [language codes](/docs/speech-to-text/pre-recorded-audio/code-switching), you can use the `language_codes` parameter. A max of two language codes can be set and one code must be `"en"`. For example, if your file contains both English and Spanish, it would be `"language_codes": ["en", "es"]`.
 
 <CodeBlocks>
 
@@ -99,14 +99,14 @@ const client = new AssemblyAI({
 });
 
 // You can use a local filepath:
-const audioFile = "./bilingual-audio.mp3"
+const audioFile = "./bilingual-audio.mp3";
 
 // Or use a publicly-accessible URL:
 // const audioFile = "<AUDIO_URL>";
 
 const params = {
   audio: audioFile,
-  language_codes: ["en", "es"] // English-Spanish code switching
+  language_codes: ["en", "es"], // English-Spanish code switching
 };
 
 const run = async () => {
@@ -142,7 +142,7 @@ const uploadUrl = uploadResponse.data.upload_url;
 
 const data = {
   audio_url: uploadUrl,
-  language_codes: ["en", "es"]  // English-Spanish code switching
+  language_codes: ["en", "es"], // English-Spanish code switching
 };
 
 const url = `${baseUrl}/v2/transcript`;
@@ -416,13 +416,15 @@ while (true) {
 </CodeBlocks>
 
 ## Use Automatic Language Detection
- 
-To use automatic language detection for code switching, set `language_detection` to `True`. Then, within `language_detection_options` set `code_switching` to `True`. 
+
+To use automatic language detection for code switching, set `language_detection` to `True`. Then, within `language_detection_options` set `code_switching` to `True`.
 
 Optionally, you can set `code_switching_confidence_threshold` to a number between 0 and 1. This will only use identified languages above this threshold. A max of two languages can be identified.
 
 <Note title="Code Switching Confidence Threshold">
-By default, the `code_switching_confidence_threshold` parameter is set to `0.3`. If you would like to disable this, make sure to set this parameter to `0`.
+  By default, the `code_switching_confidence_threshold` parameter is set to
+  `0.3`. If you would like to disable this, make sure to set this parameter to
+  `0`.
 </Note>
 
 <CodeBlocks>
@@ -506,7 +508,7 @@ const client = new AssemblyAI({
 });
 
 // You can use a local filepath:
-const audioFile = "./bilingual-audio.mp3"
+const audioFile = "./bilingual-audio.mp3";
 
 // Or use a publicly-accessible URL:
 // const audioFile = "<AUDIO_URL>";
@@ -516,7 +518,7 @@ const params = {
   language_detection: true,
   language_detection_options: {
     code_switching: true,
-    code_switching_confidence_threshold: 0.5 // Optional parameter - this is set to 0.3 by default
+    code_switching_confidence_threshold: 0.5, // Optional parameter - this is set to 0.3 by default
   },
 };
 
@@ -556,8 +558,8 @@ const data = {
   language_detection: true,
   language_detection_options: {
     code_switching: true,
-    code_switching_confidence_threshold: 0.5 // Optional parameter - this is set to 0.3 by default
-  }
+    code_switching_confidence_threshold: 0.5, // Optional parameter - this is set to 0.3 by default
+  },
 };
 
 const url = `${baseUrl}/v2/transcript`;
@@ -870,4 +872,4 @@ If your audio contains primarily one language with only occasional words from an
 
 - [Supported Languages](/docs/speech-to-text/pre-recorded-audio/supported-languages) - View all available language options
 - [Speaker Diarization](/docs/speech-to-text/speaker-diarization) - Identify different speakers in multi-speaker conversations
-- [Custom Vocabulary](/docs/guides/custom-vocab-lemur) - Boost transcription accuracy using LeMUR
+- [Keyterms Prompt](/docs/pre-recorded-audio/improving-transcript-accuracy) - Boost transcription accuracy
diff --git a/fern/pages/02-speech-to-text/pre-recorded-audio/select-the-region.mdx b/fern/pages/02-speech-to-text/pre-recorded-audio/select-the-region.mdx
@@ -5,7 +5,7 @@ title: "Select the Region"
 The default region is US, with base URL `api.assemblyai.com`. For EU data residency requirements, you can use our base URL for EU at `api.eu.assemblyai.com`.
 
 <Note>
-  The base URL for EU is currently only available for Async transcription and LeMUR.
+  The base URL for EU is currently only available for Async transcription.
 </Note>
 
 | Region       | Base URL                |
diff --git a/fern/pages/03-audio-intelligence/auto-chapters.mdx b/fern/pages/03-audio-intelligence/auto-chapters.mdx
@@ -512,10 +512,10 @@ while (true) {
 29610-280340: High particulate matter in wildfire smoke can lead to serious health problems
 ```
 
-<Tip title="Auto Chapters Using LeMUR">
+<Tip title="Auto Chapters Using LLM Gateway">
   Check out this cookbook [Creating Chapter
-  Summaries](/docs/guides/input-text-chapters) for an example of how to leverage
-  LeMUR's custom text input parameter for chapter summaries.
+  Summaries](/docs/guides/input-text-chapters) for an example of how to use LLM
+  Gateway to create chapter summaries.
 </Tip>
 
 ## API reference
diff --git a/fern/pages/03-audio-intelligence/pii-redaction.mdx b/fern/pages/03-audio-intelligence/pii-redaction.mdx
@@ -134,7 +134,7 @@ print(transcript.text)
   </Tab>
   <Tab language="python" title="Python" default>
 
-  Enable Topic Detection by setting `redact_pii` to `True` in the JSON payload.
+Enable Topic Detection by setting `redact_pii` to `True` in the JSON payload.
 
 Set `redact_pii_policies` to specify the information you want to redact. For the full list of policies, see [PII policies](#pii-policies).
 
@@ -187,7 +187,7 @@ while True:
   </Tab>
   <Tab language="javascript-sdk" title="JavaScript SDK">
 
-  Enable PII Redaction by setting `redact_pii` to `true` in the transcription
+Enable PII Redaction by setting `redact_pii` to `true` in the transcription
 config.
 
 Use `redact_pii_policies` to specify the information you want to
@@ -280,7 +280,7 @@ while (true) {
   </Tab>
   <Tab language="csharp" title="C#">
 
-  Enable Topic Detection by setting `redact_pii` to `true` in the JSON payload.
+Enable Topic Detection by setting `redact_pii` to `true` in the JSON payload.
 
 Set `redact_pii_policies` to specify the information you want to redact. For the full list of policies, see [PII policies](#pii-policies).
 
@@ -406,7 +406,7 @@ class Program
   </Tab>
 <Tab language="ruby" title="Ruby">
 
-  Enable Topic Detection by setting `redact_pii` to `true` in the JSON payload.
+Enable Topic Detection by setting `redact_pii` to `true` in the JSON payload.
 
 Set `redact_pii_policies` to specify the information you want to redact. For the full list of policies, see [PII policies](#pii-policies).
 
@@ -575,10 +575,10 @@ of things. The season has been pretty dry already, and then the fact that we're
 getting hit in the US. Is because there's a couple of weather systems that ...
 ```
 
-<Tip title="PII Redaction Using LeMUR">
-  If you would like the option to use LeMUR for custom PII redaction, check out
-  this guide [Redact PII from Text Using
-  LeMUR](/docs/lemur/lemur-pii-redaction).
+<Tip title="PII Redaction Using LLM Gateway">
+  If you would like the option to use LLM Gateway for custom PII redaction,
+  check out this guide [Redact PII from Text Using LLM
+  Gateway](/docs/lemur/lemur-pii-redaction).
 </Tip>
 
 ## Create redacted audio files
@@ -593,8 +593,6 @@ Retrieve the redacted audio file using the `transcript_id` for a transcript wher
 
 </Tip>
 
-
-
 <Tabs groupId="language">
   <Tab value="python-sdk" title="Python SDK" default>
     To create a redacted version of the audio file, use the `set_redact_pii()` method on the `TranscriptionConfig` with `redact_audio` to `True`.
diff --git a/fern/pages/03-audio-intelligence/sentiment-analysis.mdx b/fern/pages/03-audio-intelligence/sentiment-analysis.mdx
@@ -529,10 +529,10 @@ Timestamp: 250 - 6350
 ...
 ```
 
-<Tip title="Sentiment Analysis Using LeMUR">
-  Check out this cookbook [LeMUR for Customer Call Sentiment
-  Analysis](/docs/guides/call-sentiment-analysis) for an example of how to
-  leverage LeMUR's QA feature for sentiment analysis.
+<Tip title="Sentiment Analysis Using LLM Gateway">
+  Check out this cookbook [LLM Gateway for Customer Call Sentiment
+  Analysis](/docs/guides/call-sentiment-analysis) for an example of how to use
+  LLM Gateway to analyze the sentiment of a customer call.
 </Tip>
 
 ## Add speaker labels to sentiments
diff --git a/fern/pages/03-audio-intelligence/summarization.mdx b/fern/pages/03-audio-intelligence/summarization.mdx
@@ -521,7 +521,7 @@ while (true) {
 
 <Tip title="Custom Summaries Using LeMUR">
   If you want more control of the output format, see how to generate a [Custom
-  summary using LeMUR](/docs/lemur/summarize-audio).
+  summary using LLM Gateway](/docs/llm-gateway/apply-llms-to-audio-files).
 </Tip>
 
 ## API reference
diff --git a/fern/pages/03-audio-intelligence/topic-detection.mdx b/fern/pages/03-audio-intelligence/topic-detection.mdx
@@ -623,9 +623,9 @@ Audio is 93.78% relevant to Home&Garden>IndoorEnvironmentalQuality
 ...
 ```
 
-<Tip title="Topic Detection Using LeMUR">
+<Tip title="Topic Detection Using LLM Gateway">
   Check out this cookbook [Custom Topic Tags](/docs/guides/custom-topic-tags)
-  for an example of how to leverage LeMUR for custom topic detection.
+  for an example of how to use LLM Gateway to create custom topic tags.
 </Tip>
 
 ## API reference
diff --git a/fern/pages/04-lemur/summarize-audio.mdx b/fern/pages/04-lemur/summarize-audio.mdx
@@ -12,7 +12,7 @@ If you want a Quickstart, see [Apply LLMs to audio files](/docs/lemur/apply-llms
 
 ## Basic summary example
 
-If you want to send a custom prompt to the LLM, you can use the [LeMUR Task](https://assemblyai.com/docs/api-reference/lemur/task) endpoint to apply the model to your transcribed audio files.
+If you want to send a custom prompt to an LLM, you can use [LLM Gateway](/docs/llm-gateway/overview) to summarize your audio data.
 
 <Tabs groupId="language">
 <Tab language="python-sdk" title="Python SDK" default>
@@ -32,9 +32,11 @@ transcriber = aai.Transcriber()
 transcript = transcriber.transcribe(audio_file)
 
 # Step 2: Define a summarization prompt.
+
 prompt = "Provide a brief summary of the transcript."
 
 # Step 3: Apply LeMUR.
+
 result = transcript.lemur.task(
 prompt, final_model=aai.LemurModel.claude_sonnet_4_20250514
 )
diff --git a/fern/pages/05-guides/automatic-language-detection-workflow.mdx b/fern/pages/05-guides/automatic-language-detection-workflow.mdx
@@ -14,7 +14,7 @@ Performing ALD with this workflow has a few benefits:
 - Ability to detect 99 languages
 - Ability to use Nano as fallback if the language is not supported in Universal
 - Ability to enable [Audio Intelligence models](/audio-intelligence) if the [language is supported](/docs/speech-to-text/pre-recorded-audio/supported-languages)
-- Ability to use [LeMUR](/lemur) with LLM prompts in Spanish for Spanish audio
+- Ability to use [LLM Gateway](/llm-gateway) with LLM prompts in Spanish for Spanish audio
 
 ## Before you begin
 
diff --git a/fern/pages/05-guides/cookbooks/core-transcription/translate_transcripts.mdx b/fern/pages/05-guides/cookbooks/core-transcription/translate_transcripts.mdx
@@ -20,7 +20,7 @@ AAI_API_TOKEN = ""
 
 **Make sure not to share this token with anyone** - it is a private key associated uniquely to your account.
 
-Next, we'll install the AssemblyAI Python SDK, which will allow us to easily use LeMUR in just a few lines of code.
+Next, we'll install the AssemblyAI Python SDK.
 
 ```bash
 pip install "assemblyai"
diff --git a/fern/pages/05-guides/lemur.mdx b/fern/pages/05-guides/lemur.mdx
@@ -165,8 +165,8 @@ Apply Large Language Models to spoken data. A Large Language Model (LLM) is a ma
 | Model/Feature          | Use with LLM Gateway                                                                   |
 | ---------------------- | -------------------------------------------------------------------------------------- |
 | **Sentiment Analysis** | [Customer Call Sentiment Analysis](call-sentiment-analysis)                            |
-| **Auto Chapters**      | [Creating Chapter Summaries with the Custom Text Input Parameter](input-text-chapters) |
-| **Summarization**      | [Create Custom Summaries using the Task Endpoint](task-endpoint-custom-summary)        |
+| **Auto Chapters**      | [Creating Chapter Summaries](input-text-chapters) |
+| **Summarization**      | [Create Custom Summaries](task-endpoint-custom-summary)        |
 | **Topic Detection**    | [Create Custom Topic Tags](custom-topic-tags)                                          |
 
 ## Use Case-Specific LLM Gateway Workflows
diff --git a/fern/pages/05-guides/pre-recorded.mdx b/fern/pages/05-guides/pre-recorded.mdx
diff --git a/fern/pages/faq/accounts-billing-pricing/how-does-pricing-work.mdx b/fern/pages/faq/accounts-billing-pricing/how-does-pricing-work.mdx
diff --git a/fern/pages/faq/async/do-we-have-resources-for-building-with-make-.mdx b/fern/pages/faq/async/do-we-have-resources-for-building-with-make-.mdx
diff --git a/fern/pages/faq/async/do-you-offer-cross-file-speaker-identification.mdx b/fern/pages/faq/async/do-you-offer-cross-file-speaker-identification.mdx
diff --git a/fern/pages/faq/privacy-security/are-you-gdpr-compliant.mdx b/fern/pages/faq/privacy-security/are-you-gdpr-compliant.mdx
diff --git a/fern/usm-streaming-overrides.yml b/fern/usm-streaming-overrides.yml
diff --git a/usm-streaming.yml b/usm-streaming.yml
