DeepGram AI Adds Filler Words Feature for Transcripts
Manage filler words in transcripts with DeepGram AI. Control inclusion by setting parameters. Ideal for LLM fine-tuning. Explore documentation for details.
File
Tracking Filler Words in Audio Transcription with Deepgram AI
Added on 01/29/2025
Speakers
add Add new speaker

Speaker 1: So, uh, do you wanna, like, keep track of your, uh, filler words? Well, look no further than DeepGram AI. By popular demand, we've recently created a brand new feature called Filler Words that gives you the ability to, you guessed it, include filler words in your transcript if you so desire. It works like any other DeepGram parameter. If you set filler words to true, like in these API calls here, our models will include every filler word you say. If you set filler words to false, our models will exclude them. You can do this for both prerecorded audio and for live streaming audio. And here's what those different transcriptions will look like.

Speaker 2: Um, or you'd want something where, uh, so let's say you're trying to fine-tune an LLM to something very specific, um, so it's not as, uh, cut and dry as, um, you know, what's the difference between a debit card and a credit card? It's something that...

Speaker 1: And that's what it looks like to keep track of your filler words. If you're curious to learn more, check out our documentation. And as always, follow DeepGram for more AI content.

ai AI Insights
Summary

Generate a brief summary highlighting the main points of the transcript.

Generate
Title

Generate a concise and relevant title for the transcript based on the main themes and content discussed.

Generate
Keywords

Identify and highlight the key words or phrases most relevant to the content of the transcript.

Generate
Enter your query
Sentiments

Analyze the emotional tone of the transcript to determine whether the sentiment is positive, negative, or neutral.

Generate
Quizzes

Create interactive quizzes based on the content of the transcript to test comprehension or engage users.

Generate
{{ secondsToHumanTime(time) }}
Back
Forward
{{ Math.round(speed * 100) / 100 }}x
{{ secondsToHumanTime(duration) }}
close
New speaker
Add speaker
close
Edit speaker
Save changes
close
Share Transcript