Skip to main content


AssemblyAI builds Speech AI models for tasks like speech-to-text, speaker diarization, speech summarization, and more. AssemblyAIโ€™s Speech AI models include accurate speech-to-text for voice data (such as calls, virtual meetings, and podcasts), speaker detection, sentiment analysis, chapter detection, PII redaction.

Installation and Setupโ€‹

Get your API key.

Install the assemblyai package.

pip install -U assemblyai

Document Loaderโ€‹

AssemblyAI Audio Transcriptโ€‹

The AssemblyAIAudioTranscriptLoader transcribes audio files with the AssemblyAI API and loads the transcribed text into documents.

See a usage example.

from langchain_community.document_loaders import AssemblyAIAudioTranscriptLoader

Help us out by providing feedback on this documentation page: