Skip to main content
Speaker diarization identifies who said what in multi-speaker audio — calls, meetings, interviews — by labeling each transcribed word with a speaker identifier.

​
Enabling diarization

Diarization is available on the WebSocket streaming endpoint. Set both fields in transcribeConfig: 
{
  "transcribeConfig": {
    "modelId": "assemblyai/u3-rt-pro",
    "audioEncoding": "LINEAR16",
    "sampleRateHertz": 16000,
    "enableSpeakerDiarization": true,
    "includeWordTimestamps": true
  }
}
Set includeWordTimestamps together with enableSpeakerDiarization — speaker labels are attached to word timestamps, not to the turn-level transcript.

​
Reading speaker labels

Each word in wordTimestamps carries a speaker identifier: 
{
  "result": {
    "transcription": {
      "transcript": "Hi, I'm calling about my account balance.",
      "isFinal": true,
      "wordTimestamps": [
        { "word": "Hi,", "startTimeMs": 97, "endTimeMs": 194, "confidence": 0.99, "speaker": 0 },
        { "word": "I'm", "startTimeMs": 698, "endTimeMs": 779, "confidence": 0.99, "speaker": 0 }
      ]
    }
  }
}
Speaker identifiers are integers assigned within a stream in order of first appearance. They mark “same speaker in this session” — they do not identify a person across sessions.
Numbering varies by provider: AssemblyAI starts at 0, Soniox at 1.
To build per-speaker segments, group consecutive words that share a speaker value. Words may occasionally arrive without a label; treat those as unattributed rather than assuming a speaker.

​
Model support

ModelSpeaker diarization
assemblyai/u3-rt-pro
assemblyai/universal-streaming-english
assemblyai/universal-streaming-multilingual
soniox/stt-rt-v4
soniox/stt-rt-v5
deepgram/flux-general-en
deepgram/flux-general-multi
inworld/inworld-stt-1Coming soon
assemblyai/whisper-rt
groq/whisper-large-v3

​
Next steps

WebSocket API Reference

Full message and configuration schema for the streaming endpoint.

Turn Detection

Detect when a speaker has finished talking.