Speaker Intelligence

Intent Detection

Classifies the intent of the full transcript using Gemini. Returns label, confidence, and reasoning.

Python SDK

python
config = TranscriptionConfig(
    model="zero-indic",
    enable_intent_detection=True,
)
result = await client.asr.transcribe("call.wav", config=config)

intent = result.nlp_analysis.intent
print(f"{intent.label} ({intent.confidence:.0%})")
# service_request (92%)
print(intent.reasoning)
# Caller is requesting roadside assistance for a broken-down vehicle

REST API

terminal
curl -X POST https://asr.shunyalabs.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer <API_KEY>" \
  -F "[email protected]" \
  -F "model=zero-indic" \
  -F "enable_intent_detection=true"

Output

json
{
  "nlp_analysis": {
    "intent": {
      "label": "service_request",
      "confidence": 0.92,
      "reasoning": "Caller is requesting roadside assistance for a broken-down vehicle"
    }
  }
}
PreviousSentiment AnalysisNext Constrained Intent