Gender detection | Smallest AI Docs

Pre-Recorded

Enabling gender detection

Append gender_detection=true to your Pulse STT query string.

Sample request

# Download sample audio (or use your own file)
curl -sL -o audio.wav "https://github.com/smallest-inc/cookbook/raw/main/speech-to-text/getting-started/samples/audio.wav"
curl --request POST \
  --url "https://api.smallest.ai/waves/v1/stt/?model=pulse&language=en&gender_detection=true" \
  --header "Authorization: Bearer $SMALLEST_API_KEY" \
  --header "Content-Type: audio/wav" \
  --data-binary "@audio.wav"

For gender detection on pre-recorded audio, use Pulse (?model=pulse, gender_detection=true) - the single gender string documented below. For gender detection on streaming audio, use Pulse 2.0 (?model=pulse-2, gender_detection=true by default) - a differently-shaped gender object per final, with a confidence score and the full score distribution.

Output format & field of interest

Responses include a top-level gender (male, female) field that describes the dominant speaker in the processed segment. Store this field next to each transcript to power demographic analytics or routing logic.

Sample response

{
  "status": "success",
  "transcription": "Hello world.",
  "gender": "male"
}