Privacy and data
How SparkVox handles your audio, transcripts, and voice profile.
Project audio and video are transcribed via Gladia (diarized when needed). Raw audio for URL and upload projects is stored temporarily during processing, then removed after the transcript is saved.
Post text is generated with Anthropic Claude. Optional images use fal.ai and Google Imagen, then are served from SparkVox media storage. Your voice profile is built from your transcripts and optional edit feedback - not from LinkedIn scraping. Posts sound like you because they are derived from what you said, not from a public profile scrape.
Your data is never used to train models for other users. Full details in our privacy policy at sparkvox.io/privacy.