Create Knowledge Upload
create_knowledge_uploadSend a file from the user's own computer into a notebook, for a client that can run a command there (Codex, Claude Code, Cursor): a recording to transcribe (.mp3 .m4a .wav .ogg .webm .flac .mp4 .mpeg .mpga, WhatsApp voice notes .opus, .aac .amr .3gp .3ga .wma .oga) or a document (.pdf .docx .txt .md .csv .tsv), up to 1 GB. Give the file name and its exact size_bytes, and sha256 when you can. Returns an upload_url and ready commands: one curl PUT for a file up to 32 MB, else a short Python script that sends 32 MB chunks with Content-Range and resumes after an interruption. Run the command on the computer that holds the file; the bytes never pass through the conversation. Without notebook_id a new notebook named after the file (or title) is made when the last byte arrives. A recording takes one place in the account's transcription allowance, which depends on its plan and renews with its credits; the reply says how many places are left. Follow it with get_knowledge_upload.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"filename": "<filename>",
"size_bytes": "<size_bytes>"
},
"name": "create_knowledge_upload"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| title | No | Title for the new notebook, when notebook_id is omitted. | |
| app_id | No | Optional app whose notebooks to use. Omitted: the owner's own Business Brain. | |
| sha256 | No | Optional hex sha256 of the file; a mismatch is refused. | |
| filename | Yes | The file's name with its extension, e.g. meeting-11-12.m4a. | |
| folder_id | No | Folder for the new notebook. | |
| size_bytes | Yes | The exact file size in bytes. | |
| notebook_id | No | Optional: an existing notebook. Omitted: a new one. | |
| content_type | No |