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 - Purpose: Start a removal job for a source video. Returns a
filler_word_removal_idto poll.
202 Accepted immediately; the job runs asynchronously. video takes a public HTTPS URL or an asset_id from POST /v3/assets (see Upload Assets). 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 has the rest.
Idempotency
Pass anIdempotency-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} 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_cutscounts filler cuts only. A job that trimmed silences alone reportsnum_cuts: 0with a positivereduction_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.
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.callback_url over tight polling: HeyGen will POST you the finished job instead (filler_word_removal.success / filler_word_removal.fail webhook events), 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 for highlights, and score the cuts with background music and sound effects from the same Tools suite.
