Early-childhood speech analysis

Use the Nova 1 model for early-childhood speech analysis. It is designed for young speakers from approximately six months to eight years old and accounts for variation in children’s voices, pronunciations, and developing speech patterns.

Select Nova 1

Set the model field in your request:

model=nova-1

For example:

curl -s -X POST https://api.langcraft.world/v1/speech/analyze \
  -H "x-api-key: $LANGCRAFT_API_KEY" \
  -F "[email protected]" \
  -F "reference_text=the red house" \
  -F "lang=en" \
  -F "model=nova-1"

All other request fields and the response format remain unchanged. Alternatively, sending speaker_profile=early_childhood also selects Nova 1:

speaker_profile=early_childhood

Send either selector. If both fields are included, model must be nova-1. Nova 1 requires supplied reference text or reference phones.

Supported languages

Nova 1 currently supports:

English (en)
French (fr)
German (de)
Portuguese (pt)
Spanish (es)

We plan to expand Nova 1 to additional languages.

Getting started

Reference

Preview

Select Nova 1

Supported languages

​Select Nova 1

​Supported languages

Select Nova 1

Supported languages