Skip to main content
POST
/
v1
/
enhancer
/
filler_words
/
detect
Filler Words Detect
curl --request POST \
  --url https://apis.finevoice.ai/v1/enhancer/filler_words/detect \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "url": "https://example.com/audio.mp3",
  "output_format": "wav",
  "use_whisper": false,
  "whisper_model_size": "base",
  "language": "en",
  "filler_words_list": "um,uh,er,hmm,hm,ah,eh,mhm"
}
'
{}

Authorizations

​
Authorization
string
header
required

Bearer token (API key). Format: Bearer {your_api_key}

Body

application/json

The filler words detect/remove request payload.

​
url
string

Audio URL (http/https).

Example:

"https://example.com/audio.mp3"

​
output_format
string
default:wav

Output format: wav, mp3, flac, or m4a.

​
use_whisper
boolean
default:false

Use Whisper ASR for accurate, language-aware filler word detection.

​
whisper_model_size
string
default:base

Whisper model size: tiny, base, small, or medium. Used when use_whisper is true.

​
language
string
default:en

Language code for Whisper (e.g. en, zh, ja, fr). Used when use_whisper is true.

​
filler_words_list
string
default:um,uh,er,hmm,hm,ah,eh,mhm

Comma-separated filler words to detect/remove. Empty = built-in defaults.

Response

Filler word timestamps returned.

The response is of type object.