Overview | AssemblyAI | Documentation

AssemblyAI’s Streaming Speech-to-Text (STT) allows you to transcribe live audio streams with high accuracy and low latency. By streaming your audio data to our secure WebSocket API, you can receive transcripts back within a few hundred milliseconds.

Basic Streaming Workflows

Using real-time streaming
Transcribe System Audio in Real-Time (macOS)
Terminate Streaming Session After Inactivity
Migrate from Streaming v2 to Streaming v3 (Python)
Migrate from Streaming v2 to Streaming v3 (JavaScript)

Streaming for Front-End Applications

Next.js Example Using Streaming STT
Vanilla JavaScript Front-End Examples

Streaming with LLM Gateway

Use LLM Gateway with Streaming Speech-to-Text (STT)
Translate Streaming STT Transcripts with LLM Gateway

Use Case Specific Streaming Workflows

Apply Noise Reduction to Audio for Streaming Speech-to-Text
Transcribe Audio Files with Streaming Speech-to-Text
Evaluate Streaming transcription accuracy with WER
Determine Optimal Turn Detection Settings from Historical Audio Analysis