Keyword boosting
The keywords
parameter improves recognition accuracy for specific words.
Currently supported for Korean speech.
Name | Type | Description | Example (sommers) | Example (whisper) |
---|---|---|---|---|
keywords | array | List of keywords to boost accuracy | ["에스티티", "에이피아이"] | ["stt", "에스티티", "Whisper V2", "Api"] |
caution
- For
sommers
, write keywords in Korean phonetics. - For
whisper
, keywords can be Korean, English acronyms, and numbers. Case-insensitive for English. - Max 500 words, each ≤ 20 chars.
Usage
In the POST Request body, set keywords
to a list of words.
POST example: Example
Unified example (presets): Example
Example improvement
When requesting transcription with keywords
of ["음성인식"], an output such as "음성의식" may be corrected to "음성인식".
{
"id": "G6j7wIYxSCCz3gYtQbeYdQ",
"status": "completed",
"results": {
"utterances": [
{
"start_at": 1187,
"duration": 600,
"spk": 0,
"spk_type": "NORMAL",
- "msg": "리턴제로는 음성의식을 하는 회사입니다."
+ "msg": "리턴제로는 음성인식을 하는 회사입니다."
}
]
}
}