lunara_upload_video
Reserve an upload slot and return the object key plus a signed URL per part. After uploading the bytes call lunara_finish_upload. Use this for a file you hold locally.
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>",
"mime": "<mime>",
"sizeBytes": "<sizeBytes>"
},
"name": "lunara_upload_video"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mime | Yes | MIME type, e.g. audio/mpeg, video/mp4. | |
| filename | Yes | Original filename, used for the download name. | |
| projectId | No | Project to upload into. Omit to let Lunara reuse the most recent project for this organisation. | |
| sizeBytes | Yes | Exact file size in bytes. | |
| sourceLang | No | What the speaker is actually speaking, in BCP-47 form: "yue-Hant-HK" Cantonese, "cmn-Hans-CN" Mandarin, "en-US" English, "ja-JP" Japanese, "ko-KR" Korean. Default "auto" (detect). This is INDEPENDENT of primaryLang/secondaryLang, which are the TEXT tracks you want back — e.g. English speech with primaryLang "zh-Hant" and secondaryLang "en" means "listen in English, give me Chinese and English subtitles". | |
| spokenLang | No | Alias of sourceLang — same value. Use whichever the other tools call it. | |
| primaryLang | No | Written-track language. Default yue-Hant. | |
| secondaryLang | No | Translated-track language. Default en. | |
| secondaryLangs | No | Translation languages to produce in the same job (max 16). Merged with secondaryLang. Each one costs a separate translation pass; the speech is transcribed once. | |
| clientOperationId | No | Idempotency key. Reuse the same value to retry without creating a second upload. |