ic_transcribe_submit
ActiveTool of Immersive Commons
Queue an audio file for offline transcription + speaker diarization by IC's GPU worker. Provide EXACTLY ONE source: a file_id you uploaded via ic_files_put (audio <=25MB) OR an https audio_url. Results (a markdown transcript + a JSON with per-speaker segments) land in the file vault next to the source; poll ic_transcribe_status no more than once per minute, then read the transcript with ic_transcribe_get. Args: { file_id?, audio_url?, language? (BCP-47 hint, e.g. 'en'), num_speakers_hint? (1..10) }. Returns: { ok, id, status: 'queued', queue_position }. Rate: 5 submissions per token per UTC day. Required scope: transcribe:submit (ic-member+).
Parameters schema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"file_id": {
"type": "string",
"maxLength": 64,
"description": "A vault file id (f_...) from ic_files_put. Mutually exclusive with audio_url."
},
"language": {
"type": "string",
"maxLength": 16,
"description": "Optional BCP-47 language hint (e.g. 'en', 'es'). Omit to auto-detect."
},
"audio_url": {
"type": "string",
"maxLength": 2048,
"description": "An https URL to the audio. Mutually exclusive with file_id. No private/loopback hosts."
},
"num_speakers_hint": {
"type": "integer",
"maximum": 10,
"minimum": 1,
"description": "Optional hint for how many speakers to diarize (1..10)."
}
}
}No endpoints wrapped at confidence ≥ 0.70.
Parent server
Immersive Commons
https://github.com/immersive-commons/ic-skills
1/7 registries