AUDIOVISUAL CORPUS WORKBENCH
Find language in the wild.
Build reproducible concordances from timestamped audiovisual transcripts.
Registration is controlled by an administrator.
Create account
We will send a verification link to your email address. Set your password using that link.
Verify email and set password
ADMINISTRATION
User management
Registration settings
Create account
Accounts
| Username | Role | Status | Corpora | Actions |
|---|
ACCOUNT SETTINGS
Data providers
Filmot
Use your own Filmot subscription and API allowance. Your key is stored encrypted on the server and is not returned to the browser.
Saved does not mean verified. Live requests use your own credits. Ensure your use and retention of transcripts is lawful.
Other providers
Podscan and Pod Engine are planned. Timestamped local JSON and SRT/VTT imports are supported now.
Local workers
Install the separate local-worker folder on your computer. Audio and Whisper run there, never on the server. Use only media you are permitted to download and process.
RESEARCH WORKSPACE
Your corpora
Create a sample, annotate transcripts, and explore concordances.
NEW CORPUS
Define your sampling frame
CORPUS OVERVIEW
Search corpus
View options
Browse transcripts
Reannotate stored transcripts (no API calls)
Creates a new corpus from the original raw cues, not manual corrections. The existing corpus and its correction history remain unchanged.
| Left context | KW | Right context | Source / time |
|---|