Automated API audio parsing for Salesforce CRM intelligence
Automated API audio parsing for Salesforce CRM intelligence converts each audio recording attached to a record into searchable passages, so the assistant answers from the file rather than from fields someone typed.
How does automated API audio parsing feed Salesforce CRM intelligence?
Automated API audio parsing for Salesforce CRM intelligence converts each attached audio recording into passages when the file is saved, so the assistant can cite the file instead of guessing from record fields.
Where the audio recording 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 audio recording is not, until automated API audio 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 an audio file actually yields
WAV and FLAC decode in the converter, and speech transcription is what turns them into passages. There is no text layer to extract. MP3, M4A, AAC, OGG, and Opus are audio to a person and still need a demuxer this tree does not have, so they are not a silent success: convert them to WAV before ingest. A recording that never reaches the transcriber stays out of the index.
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 audio recording inside chat for every question never builds that index. Automated API audio 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 audio recording 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 audio.