Content and transcripts
The service stores the debate trees, arguments, comments, votes, and evaluation criteria you create. It also stores video metadata, including the original file name, title, duration, thumbnail, and channel name; transcript text and the transcription provider's raw response; live-session state; argument text kept so a score can be reused; and an audit log of language-model calls. That log includes the system prompt, the user prompt, the raw response, the provider, the model, and token counts. The tree owner and collaborators with admin access can read those logs.
Audio and video you upload, up to 500MB, are sent to AssemblyAI for transcription. We keep the transcript and file metadata. We do not keep the uploaded file itself unless you tick "Keep this recording for playback" when you upload it, which is off by default. A YouTube address is sent to Firecrawl so we can obtain a short-lived audio address, which is then sent to AssemblyAI. We do not keep that temporary audio address.
During a live conversation, audio is streamed from your browser, or from a stream you send us, to AssemblyAI after the server issues a short-lived streaming token. We do not keep that audio unless the person running the session turns on "Save audio for playback", which is off by default.
When saving is on, a compressed recording of the session, or the recording you uploaded, is stored in private storage at Supabase so the transcript can be checked against it. Only the tree's owner and the editors they invite can play it. It can be played for 90 days and is then deleted from storage; the owner can delete it sooner, and deleting the tree deletes it. The person running the session is responsible for telling everyone they are being recorded.