Analysis is what turns raw files into footage you can search, read, and edit. Selects transcribes every file, breaks it into topics, identifies who is speaking, and reads what is on screen.
Nothing is analyzed automatically. You decide when to run it, and you are only charged for what finishes.
Start analysis
Analysis covers every file in the project, so remove anything you do not need before you start. Fewer files means a faster, cheaper run.
Check what the analysis will cover and what it will cost first. See Import Footage and Start a Project.
When you are ready:
Click [Analyze media for edit] in the top bar.
Selects asks you to double-check your sync. Confirm your multicam and separate audio are aligned.
Click [Start analysis].
Note: Check your sync carefully at this step. Transcription is built on the synced audio, so a bad sync cannot be repaired after analysis has run. See Sync your files.
What happens while analysis runs
Selects works through each file in turn: preparing the audio, detecting silences, transcribing, dividing the transcript into topics, and finding key visual moments.
The progress screen tells you roughly how long is left.
Click the progress line to expand it and see every file, which one is running, and which have finished or failed.
You can keep working in Selects while analysis runs. Just leave the app open, because analysis stops if Selects quits.
Tip: Leave [Keep this computer awake] switched on. If your computer sleeps partway through, analysis can fail. Your display can still turn off, but closing a laptop lid will still put the machine to sleep.
To stop early, click [Stop analysis]. Files that already finished are kept, and when you resume, you are not charged for them a second time.
What you get after analysis
Transcription. Every file gets its own transcript: each video, each audio file, and each synced timeline. A synced timeline is transcribed as a single unit, not as its separate camera angles. Every word is time-stamped, so you can edit by reading rather than scrubbing. See Refine Your Draft.
Topics and subtopics. Just like the transcript, every file gets its own topics and subtopics. Selects reads the transcript and organizes each file into topics and subtopics, so you can see what the footage covers at a glance. See What are Topics and Subtopics.
Speaker detection. Selects identifies each speaker in a file and works out which audio sources belong to them. On multicam footage, it also scores the camera angles against each speaker, which is what camera switching uses later. You can rename, reassign, or add a speaker at any time.
Visual analysis. Selects reads what is on screen and writes a short description for each clip. This is what scene search matches against, so you can find a moment by describing it. See Search Your Footage: Text and Scene Search.
Shot quality. Selects marks stretches that are shaky or out of focus, and stretches where a speaker is facing the camera, per camera angle.
Every file stands on its own. Each one gets its own transcript, topics, subtopics, and speakers, whether it is a single video, an audio file, or a synced timeline.
Once analysis finishes, Selects asks how you want to start the edit: a stringout, an assembly cut, matching a script, or building it yourself.
Analyze files you add later
Files added after a project is created are not analyzed automatically either.
Hover a file in the project panel and click [Analyze] to run it on its own. The same button appears on a synced timeline row, and on any file whose analysis failed, so you can retry just that one. While a single file is running you can click [Cancel] to stop it.
You can also analyze from the timeline. Selects shows you the files and the estimated credits first, then starts once you confirm. See Add media to an existing project.
Credits
Analysis uses credits from your plan balance:
Video analysis: 1 credit per 10 seconds (6 credits/min, 360 credits/hr)
Audio analysis: 1 credit per minute (60 credits/hr)
Image analysis: 1 credit per image
You only pay for analysis that succeeds. Files that fail are never charged, files you have already analyzed are never charged twice, and stopping partway does not re-charge the files that finished.
FAQs
Does Selects analyze my footage automatically?
No. You choose when to run it. Dropping files into a project, or adding them later, does not start analysis or use any credits.
Can I analyze only some of my files?
On the prep page, analysis covers every file in the project, so remove anything you do not need before you start. Files you add to a project later work differently: each one gets its own [Analyze] button, so you can run them one at a time.
How long does analysis take?
Roughly 20 minutes for every hour of video, though it varies with your internet connection and your machine. The progress screen gives you an estimate once it has enough to go on. We are working on making this faster.
Can I use Selects while analysis is running?
Yes. You can move around the app and keep working while it runs. Leave Selects open, though, because analysis stops if you quit the app.
What happens if analysis fails on some files?
The rest carry on and land on your timeline as normal, and you are not charged for the ones that failed. You can retry a failed file on its own: hover it in the project panel and click [Analyze].
Can I stop analysis and pick it up later?
Yes. Click [Stop analysis] to stop. Anything that already finished is kept, and resuming does not charge you again for those files.
What languages does Selects support for transcription?
Selects supports transcription in over 90 languages.
Supported languages: Afrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Azerbaijani, Bashkir, Basque, Belarusian, Bengali, Bosnian, Breton, Bulgarian, Burmese, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Faroese, Finnish, Flemish, French, Galician, Georgian, German, Greek, Gujarati, Haitian Creole, Hausa, Hawaiian, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Korean, Lao, Latin, Latvian, Lingala, Lithuanian, Luxembourgish, Macedonian, Malagasy, Malay, Malayalam, Maltese, Maori, Marathi, Mongolian, Nepali, Norwegian, Norwegian Nynorsk, Occitan, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Sanskrit, Serbian, Shona, Sindhi, Sinhala, Slovak, Slovenian, Somali, Spanish, Spanglish, Sundanese, Swahili, Swedish, Tagalog, Tajik, Tamil, Tatar, Telugu, Thai, Tibetan, Turkish, Turkmen, Ukrainian, Urdu, Uzbek, Vietnamese, Welsh, Yiddish, Yoruba.
Note: Transcription accuracy can vary by language and by audio quality, such as background noise or overlapping speakers.