The HD version has less static noise in most situations at the cost of higher latency. Read more about the OpenAI voices and models here.
Adjust the detected face bounding box. Often leads to improved results. Recommended to give at least 10 padding for the chin region.
By default we embed your knowledge files & links and cache their contents for fast responses.
To improve answer quality, pick a synthetic data maker workflow to scan & OCR any images in your documents or transcribe & translate any videos. It also can synthesize a helpful FAQ. Adds ~2 minutes of one-time processing per file.