Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.illocution.ai/llms.txt

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

​
When to Use

Upload a finished recording but receive the same SSE signals you would see in a live call. Ideal for coaching apps that want incremental results without implementing chunked uploads.

​
Request

​
file
binary
required
Audio or video file (mp4, mov, webm, mp3, wav, m4a, aac). Sent as multipart/form-data.

​
Response

An SSE connection (text/event-stream). Events are emitted in order:
  1. status (phase=start)
  2. final_transcript (per utterance once finalized)
  3. For each utterance: emotion, cognitive, optional transition / moment
  4. summary_update after the timeline completes
  5. status (phase=completed)
  6. done
Example CLI invocation: 
curl -N https://api.illocution.ai/analyze/stream \
  -H "Accept: text/event-stream" \
  -H "X-API-Key: $ILLOCUTION_KEY" \
  -F "file=@call.mp4"

​
Example Event

event: emotion
data: {
  "utterance_id": "analysis_1234_utt_0007",
  "speaker_id": "Speaker_1",
  "emotion": {"joy":0.64,"fear":0.05,...},
  "scores": {"valence":0.41,"arousal":0.58,"dominance":0.52},
  "confidence":0.78,
  "stability":"final"
}
POST /analyze?stream=true is a convenience alias for clients that cannot change URLs.