> ## Documentation Index
> Fetch the complete documentation index at: https://heygen-1fa696a7.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Filler word removal

> Remove filler words and overlong silences from a finished video with the HeyGen Filler Word Removal API — submit a video, get back one cleaned cut with removal statistics.

![](https://mintcdn.com/heygen-1fa696a7/hfMXXwJzjE7vBSYZ/images/theme/research-5.webp?fit=max\&auto=format\&n=hfMXXwJzjE7vBSYZ\&q=85\&s=422da140ece4b799d490f85bb2013ca5)

Submit a video and get back a cleaned version with the "um"s, "uh"s, and overlong silences cut out. The job transcribes the audio, detects filler words, removes them along with dead air, and renders one finished video, with no review step or edit decisions to make. It's built for recordings where a human spoke off the cuff: webinars, screen recordings, interviews, all-hands.

## Create a Removal Job

* Endpoint: [`POST /v3/filler-word-removals`](https://heygen-1fa696a7.mintlify.site/reference/create-filler-word-removal)
* Purpose: Start a removal job for a source video. Returns a `filler_word_removal_id` to poll.

```bash theme={null}
curl -X POST "https://api.heygen.com/v3/filler-word-removals" \
  -H "X-Api-Key: $HEYGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "video": { "type": "url", "url": "https://example.com/webinar.mp4" },
    "title": "Q3 webinar, cleaned"
  }'
```

The endpoint returns `202 Accepted` immediately; the job runs asynchronously. `video` takes a public HTTPS URL or an `asset_id` from [`POST /v3/assets`](https://heygen-1fa696a7.mintlify.site/reference/upload-asset) (see [Upload Assets](https://heygen-1fa696a7.mintlify.site/docs/upload-assets.md)). Either way, the source needs a speech audio track to transcribe and can be up to 2 hours long. `title` defaults to `Filler Removal`; the [create reference](https://heygen-1fa696a7.mintlify.site/reference/create-filler-word-removal.md) has the rest.

### Idempotency

Pass an `Idempotency-Key` header to make retries safe: replaying the same key returns the original job instead of creating a duplicate.

## Get a Removal Job

[`GET /v3/filler-word-removals/{filler_word_removal_id}`](https://heygen-1fa696a7.mintlify.site/reference/get-filler-word-removal) returns the job's `status` (`pending` → `running` → `completed` | `failed`) and `progress`. Once it completes, it carries the cleaned video's pre-signed `video_url` plus removal statistics: `original_duration`, `output_duration`, `num_cuts` and `reduction_pct`. On failure, read `failure_message`.

* `num_cuts` counts filler cuts only. A job that trimmed silences alone reports `num_cuts: 0` with a positive `reduction_pct`.
* A completed job always carries a `video_url`. When the run finds nothing to cut, the output is a copy of the original video and the charge is automatically refunded, so your polling code never needs a special no-change branch.

> [!NOTE]
>
> `video_url` is a pre-signed link with a limited lifetime. Download the file soon after the job completes, or re-fetch this endpoint for a fresh link.

For long recordings, prefer a [`callback_url`](https://heygen-1fa696a7.mintlify.site/docs/webhooks) over tight polling: HeyGen will POST you the finished job instead (`filler_word_removal.success` / `filler_word_removal.fail` [webhook events](https://heygen-1fa696a7.mintlify.site/docs/webhook-events.md)), echoing your `callback_id`. Treat the webhook as a completion signal and fetch the authoritative result from the get endpoint.

Cleaning a recording before repurposing it? Run filler removal first, then hand the cleaned video to [AI clipping](https://heygen-1fa696a7.mintlify.site/ai-clipping.md) for highlights, and score the cuts with [background music](https://heygen-1fa696a7.mintlify.site/background-music.md) and [sound effects](https://heygen-1fa696a7.mintlify.site/sound-effects.md) from the same Tools suite.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.