model = "nvidia/nemotron-3-5-transcribe").timestamps: true): outputs per-word start / end times and <spk:N> speaker turns.target_language): translates speech into or from English (timestamps: true and target_language cannot be combined in the same request).duration in seconds, rounded up to whole seconds at the per-minute rate on Emix Pricing).GET /api/v1/client/tasks/{taskId} (Get Task Details) returns state: "success", resultJson is a JSON string containing result_object:{
"result_object": {
"text": "Thanks for joining, everyone. Let's start with the launch checklist.",
"duration": 12.64,
"url": "https://tempfile.aiquickdraw.com/example/transcript-result.json",
"expires_at": "2026-12-01T12:30:23Z"
}
}result_object.url (which includes words, text_with_speakers, and diarization when timestamps: true) before expires_at (~14 days). For webhook callbacks, see Webhook Security Verification.curl --location 'https://api.emix.ai/api/v1/client/tasks' \
--header 'Content-Type: application/json' \
--data '{
"model": "nvidia/nemotron-3-5-transcribe",
"callBackUrl": "https://your-domain.com/api/callback",
"input": {
"audio_url": "https://static.aiquickdraw.com/tools/example/1793873594707_8fvLCiGf.mp3",
"timestamps": true
}
}'{
"code": 200,
"msg": "success",
"data": {
"taskId": "a1b2c3d4e5f678901234567890abcdef"
}
}