Skip to main content

Documentation Index

Fetch the complete documentation index at: https://assemblyai.com/docs/llms.txt

Use this file to discover all available pages before exploring further.

​
Overview

Each example below is a self-contained script that wires together several AssemblyAI products into a working pipeline. Run one, see the polished output, and customize from there.
Every example uses placeholder API keys (YOUR_API_KEY). Replace them with your actual key from the AssemblyAI dashboard.

​
Pre-recorded pipelines

These pipelines transcribe an existing audio file, then enrich the transcript with Speech Understanding features and LLM Gateway analysis.
PipelineProducts usedBest for
Meeting notetakerSTT + speaker diarization + Speaker Identification + language detection + LLM GatewayTeam meetings, standups, all-hands
Sales call intelligenceSTT + speaker diarization + Speaker Identification + sentiment analysis + LLM GatewayRevenue teams, coaching, QA
Medical scribeSTT + speaker diarization + Speaker Identification + Medical Mode + entity detection + LLM GatewayClinical documentation, SOAP notes
Content repurposingSTT + key phrases + LLM GatewayPodcasts, webinars, marketing

​
Streaming pipelines

These pipelines use the Streaming STT API to transcribe audio in real time from a microphone, with optional LLM Gateway integration for live analysis.
PipelineProducts usedBest for
Real-time meeting assistantStreaming STT + Universal-3 Pro + LLM GatewayLive captions, real-time summaries
Real-time live captionerStreaming STT + keyterms promptingAccessibility, live events

​
Customize and extend

Each pipeline above is a starting point. Here are common ways to build on them:
  • Swap LLM models — Change the model parameter in LLM Gateway requests to use any of the 25+ supported models (Claude, GPT, Gemini, and more).
  • Add structured output — Use Structured Outputs to constrain LLM responses to a JSON schema for easier downstream processing.
  • Add PII redaction — Enable PII Redaction to automatically mask sensitive information before it reaches the LLM.
  • Use Speaker Identification — Replace generic speaker labels with real names using Speaker Identification.
  • Add Translation — Translate transcripts into 20+ languages using Translation.
  • Use webhooks — Replace polling with webhooks for production workloads so your server gets notified when transcription completes.

​
Next steps