AssemblyAI

Automate speech-to-text transcription and analysis with AssemblyAI and emma

With emma's AssemblyAI integration, you can automate high-accuracy transcription of audio and video files, speaker diarization, summarization, sentiment analysis, and LLM analysis through automated workflows. Supports 99+ languages.

Supported Formats

Audio Files

MP3, WAV, M4A, FLAC, OGG, WebM

Video Files

MP4, MOV, MKV, WebM

Max File Size

5GB

Max Duration

10 hours

Available Tools

Authentication

API Key:API Key

Authenticate using your AssemblyAI API key to access transcription and analysis features.

8 tools are available:

Category

Tool Count

Transcription

	Tool Name	Description
	assemblyai_transcribe	Transcribe audio/video files to text with high accuracy
	assemblyai_get_transcript	Retrieve an existing transcript
	assemblyai_list_transcripts	List all transcripts
	assemblyai_delete_transcript	Delete a transcript

LLM Gateway (LeMUR)

	Tool Name	Description
	assemblyai_lemur_task	Run custom LLM analysis with prompts
	assemblyai_lemur_summary	Generate summaries of transcripts
	assemblyai_lemur_qa	Get answers to multiple questions
	assemblyai_lemur_action_items	Extract action items from meetings

Audio Intelligence Features

Feature	Description
speaker_labels	Speaker diarization (identify who said what)
auto_chapters	Auto chapters (divide into logical sections)
summarization	Automatic summarization (bullets, paragraph, etc.)
sentiment_analysis	Sentiment analysis (positive/neutral/negative)
entity_detection	Entity detection (people, organizations, locations, etc.)
content_safety	Content safety check (detect sensitive content)

Prerequisites

• emma account
• AssemblyAI account
• AssemblyAI API Key

Setup

1. Get AssemblyAI API Key

Create an account at AssemblyAI (assemblyai.com)
Get your API key from the dashboard
Copy the API key

2. Configure API Key in emma

Set your API key in emma's integration settings page.

PreviousSupabase

NextElevenLabs