Integration

AssemblyAI integration

Advanced speech-to-text and audio intelligence API for transcribing audio and video files with AI-powered features. Supports speaker diarization, sentiment analysis, entity detection, automatic chapter generation, content safety labeling, and AI summarization. Includes real-time transcription capabilities and LeMUR AI for custom transcript analysis tasks.

Connect AssemblyAI How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in AssemblyAI.Built from the 13 AssemblyAI tools below, on the connection you add once.

Common AssemblyAI use cases

Comply with GDPR data deletion requests
Add subtitles to YouTube videos
Convert podcast to blog post format
Check if transcription job has completed
Find specific topics in podcast episodes
Upload recorded meetings for transcription
Display dashboard of all transcription jobs
Download privacy-compliant audio for sharing
Extract action items from meeting transcripts
Retrieve cached LeMUR responses for dashboard display

What you can do with AssemblyAI

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Transcript, 8 operations

delete_transcriptDelete transcriptDELETEPermanently removes a transcription job and all associated data by its transcript ID. Deletes all stored data including the transcription text, word-level timestamps, speaker labels, chapters, sentiment analysis results, detected entities, and any...
get_paragraphsGet paragraphsGETRetrieves transcription results organized into paragraph segments with timestamps for improved readability and navigation.
get_sentencesGet sentencesGETRetrieves transcription results formatted as an array of complete sentences with timestamps and confidence scores.
get_subtitlesGet subtitlesGETExports transcription as SRT or VTT subtitle file format with customizable caption length for video integration.
get_transcriptGet transcriptGETRetrieves the status and complete results of a transcription job using its unique transcript ID. Returns comprehensive data including the full text transcript, word-level timestamps with confidence scores, speaker utterances for multi-speaker audi...
list_transcriptsList transcriptsGETRetrieves a paginated list of all transcription jobs associated with the authenticated account, sorted from newest to oldest. Supports filtering by status, date, and cursor-based pagination.
transcribeTranscribePOSTCreates a new audio transcription job by submitting an audio file URL to AssemblyAI for asynchronous processing. Supports advanced features including speaker diarization, automatic chapter generation, entity detection, sentiment analysis, content ...
word_searchWord searchGETSearches for specific words or phrases in a transcript and returns all occurrences with precise timestamps.

Lemur response, 2 operations

lemur_get_responseLemur get responseGETRetrieves a previously generated LeMUR response by its request ID for auditing or re-accessing results.
lemur_purgeLemur purgeDELETEPermanently deletes the data for a previously submitted LeMUR request including the AI response and context provided.

File, 1 operation

uploadUploadPOSTUploads local audio file to AssemblyAI storage and returns a URL for transcription processing.

Lemur task, 1 operation

lemur_taskLemur taskPOSTExecutes custom AI tasks on transcripts using LeMUR's language models with user-defined prompts for flexible analysis.

Redacted audio, 1 operation

get_redacted_audioGet redacted audioGETRetrieves the redacted audio file URL for a transcript where PII audio redaction was enabled, with sensitive information replaced by beeping sounds.

Use AssemblyAI from Claude Code, Cursor or Codex

Connect AssemblyAI in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its AssemblyAI operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect AssemblyAI

Create your workspace
Sign up free. Nothing to install.
Connect AssemblyAI once
Add your AssemblyAI connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

AssemblyAI integration FAQ

What can you do with the AssemblyAI integration?

LiveContext exposes 13 operations on AssemblyAI, covering transcript, lemur response, file and lemur task. Common uses include Comply with GDPR data deletion requests, Add subtitles to YouTube videos and Convert podcast to blog post format.