Same pipeline, five sources
Five kinds of recording, one run.
The pipeline does not care what was recorded. What differs between these five is what comes back out of it, how long the source usually is, and which decision you make before the run starts.
- 5 kinds
- Podcasts, Interviews, Webinars, Creator content, Business content
- 6 stages
- The same run whatever was recorded
- 9:16
- Every clip comes back vertical
Pick the one you have.
One run, six stages.
Whatever the recording is, it goes through the same six stages, and the job reports which one it is in and a percentage as it works. A queued or running job can be stopped and its credits come back.
Every stage in detailUpload received
The file lands in storage and its length is verified against what the browser reported.
Extracting audio
Audio is pulled out as 16 kHz mono and split into chunks.
Transcribing
Each chunk is transcribed with word-level and segment-level timings.
Finding clip candidates
A model reads the transcript and returns clip ranges, a title and a score.
Building clips
Each clip is cut, reframed to vertical 9:16 and has its captions burned in.
Ready
The finished MP4s appear in your clip list, ready to download.
The same limits on all five.
What a run takes and what it gives back does not change with the subject. Anything not listed here is not implemented.
- Supported input
- MP4, MOV, WebM
- Maximum file size
- 2 GB to 8 GB, by plan
- Maximum source length
- 60 minutes to 4 hours, by plan
- Clips per run
- 2 to 15, by plan
- Clip length
- 10 to 180 seconds, set before the run
- Output
- 1080 x 1920 or 720 x 1280, 9:16
- Output format
- MP4, H.264 video, AAC audio
- Captions
- Burned in, word-timed, 12 presets
- Usage unit
- 1 credit per rounded-up source minute
Whatever you upload, you get files back.
A finished clip is an MP4 in your clip list: 9:16, H.264 video and AAC audio. When captions are enabled they are already in the picture, and can be hidden before re-rendering and downloading. There is no export step and no other ratio.
