Raw schema
{
"type": "object",
"properties": {
"audio_url": {
"description": "Publicly fetchable audio file URL (wav, flac, mp3, m4a, ogg, webm; up to 30 MB / 60 minutes of English speech).",
"type": "string",
"maxLength": 2000,
"format": "uri"
},
"audio_base64": {
"description": "Base64-encoded audio bytes for local files (up to 8 MiB decoded). Prefer audio_url for anything larger.",
"type": "string",
"maxLength": 11500000
},
"filename": {
"description": "Original filename including extension (e.g. call.wav). Helps decoding when audio_base64 is used.",
"type": "string",
"maxLength": 160
},
"model": {
"description": "oruk-resonance (full local pipeline: transcription, emotion, style, affect, analysis) or oruk-fourier (parallel transcript and native 15-label emotion, with the shared 16-label style model). Resonance is the default.",
"type": "string",
"enum": [
"oruk-resonance",
"oruk-fourier"
]
},
"detail": {
"description": "compact (default) returns top label scores and condensed segments; full preserves all returned labels, segments, and word-level timings, subject to response-size limits. It does not expose unreturned label scores.",
"type": "string",
"enum": [
"compact",
"full"
]
},
"diarize": {
"description": "Label speakers (oruk-resonance only; the model is switched to oruk-resonance automatically). Speaker diarization locates turns, then Resonance scores each turn with its own text, emotions, and styles. Use for calls, meetings, and interviews. Included in subscription plan minutes. Processing details: https://oruk.ai/security#processing.",
"type": "boolean"
},
"api_key": {
"description": "Only for temporary keys from oruk_create_trial_key. Permanent keys belong in your MCP client config as an \"Authorization: Bearer <key>\" header, never in tool arguments.",
"type": "string",
"maxLength": 200
}
},
"additionalProperties": false
}