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.Streaming pipelines
These pipelines use the Real-time STT API to transcribe audio in real time from a microphone, with optional LLM Gateway integration for live analysis.Customize and extend
Each pipeline above is a starting point. Here are common ways to build on them:- Swap LLM models — Change the
modelparameter 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
- Pre-recorded STT quickstart — Step-by-step guide for your first transcription
- Real-time STT quickstart — Set up real-time transcription
- LLM Gateway overview — Explore all available models and features