Automated API video parsing for Salesforce CRM intelligence
Automated API video parsing for Salesforce CRM intelligence converts each video attached to a record into searchable passages, so the assistant answers from the file rather than from fields someone typed.
How does automated API video parsing feed Salesforce CRM intelligence?
Automated API video parsing for Salesforce CRM intelligence converts each attached video into passages when the file is saved, so the assistant can cite the file instead of guessing from record fields.
Where the video sits in Salesforce
Salesforce keeps the file on the lead, account, or opportunity as a ContentVersion or a classic Attachment. The typed fields on that record are already searchable. The video is not, until automated API video parsing copies its words into passages keyed to the same record. CRM intelligence that only reads the fields is intelligence about what a person typed, not about what the file says.
What a video actually yields
MP4, MOV, M4V, AVI, MKV, and WebM can carry speech, on-screen text, and a picture. Speech and screen text are transcriptions of words that were there. A vision description is inference and can mention an object that was never on screen, so those passages stay separate from the transcript. The decoders cover H.264, HEVC, and VP9, including the HEVC an iPhone records by default.
The API call that feeds Salesforce
An Apex trigger, a record-triggered Flow, or a Platform Event can POST those bytes when the file is saved. The response is JSONL, one passage per line, with the record id in metadata for the retrieval store beside Salesforce. Asking a model to reread the video inside chat for every question never builds that index. Automated API video parsing runs when the file is saved, once, and later questions retrieve.
What the answer is allowed to cite
After a clean parse, an answer should cite the passage and the video it came from. A file that yields no text is a skip, named as a skip, not a blank passage that crowds real hits. The parsers are Remade with Rust crates, and RAG Converter is part of MATA. The longer note on this format is RAG for meetings.