Method to Configure for Each Request

When making a speech recognition request, set the words you want to add in the profileWords request parameter. The word registration will be effective only for that session.

For example, set "AmiVoice あみぼいす" in profileWords as follows:

profileWords="AmiVoice あみぼいす"

To register multiple words, separate the notation and reading sets with a "|"(pipe). To register two words "AMI あみ" and "AOI あおい", set as follows:

profileWords="AMI あみ|AOI あおい"

Below is an example using the curl command. Here, we perform speech recognition using an audio file (test.wav). We set "AmiVoice あみぼいす|AOI あおい" in profileWords.

curl -X POST https://acp-api.amivoice.com/v1/nolog/recognize \
     -F u={APP_KEY} \
     -F "d=grammarFileNames=-a-general profileWords=AmiVoice%20%E3%81%82%E3%81%BF%E3%81%BC%E3%81%84%E3%81%99%7CAOI%20%E3%81%82%E3%81%8A%E3%81%84" \
     -F a=@test.wav