Filler Words

Filler Words can help transcribe interruptions in your audio, like "uh" and "um".

filler_words boolean. Default: false

Pre-recorded Streaming English (all available regions)

🛝
Try this feature out in our API Playground!

Deepgram is capable of transcribing the following filler words:

uh
um
mhmm
mm-mm
uh-uh
uh-huh
nuh-uh

These words will always be transcribed with the spelling listed above, regardless of their spoken duration (i.e., Deepgram will never transcribe "uhhhh" instead of "uh").

Enable Feature

To enable Filler Words you can use thefiller_words query parameter and set the value to true.

When filler_words=false or the parameter is not set, the two most common fillers, "uh" and "um", are stripped out of the transcript to improve readability.

ℹ️
Currently, Filler Words are only available for Deepgram's Nova and Nova-2 general models.

Example

curl \
  --request POST \
  --header 'Authorization: Token YOUR_DEEPGRAM_API_KEY' \
  --header 'Content-Type: audio/wav' \
  --data-binary @youraudio.wav \
  --url 'https://api.deepgram.com/v1/listen?model=nova-2&filler_words=true'

🚧
Replace YOUR_DEEPGRAM_API_KEY with your Deepgram API Key.

Results

Once applied, results will appear in the transcript.

Source	With Filler Words	Without Filler Words
uh-huh or you'd want something where uh so let's say you're trying to fine-tune a model to something very specific um so it's not as uh cut and dry as a more general task	uh-huh or you'd want something where uh so let's say you're trying to fine-tune a model to something very specific um so it's not as uh cut and dry as a more general task	uh-huh or you'd want something where so let's say you're trying to fine-tune a model to something very specific so it's not as cut and dry as a more general task

Updated 6 months ago

What’s Next

Numerals