- Clear +: Whisper can pick up background noises in audio/videos, like passerby voices, music, and even honking. Using Clear +, we remove these noises with DEMUCS and normalize the audio before sending it to Whisper for transcription.
- Subtitle Reflow: Many audio/video-to-subtitle applications group large blocks of text within the same timeframe, resulting in overly long subtitles on the screen. With our exclusive Subtitle Reflow feature, you can have context-aware cutting and time-aware segmentations, improving the viewing experience. We actually use smaller NLP models to achieve this, if you’re interested in tech spec. (Just to say don’t use LLM everywhere, it’s just too expensive and very unpredictable)
- Speaker Recognition: This feature identifies different speakers in a multi-speaker conversation, making it easier to follow who’s speaking. We use NVIDIA Nemo toolkit for state-of-the-art accuracy in Speaker Recognition.
For Stripe, I use a restricted API key with read-only access to subscriptions/invoices, plus limited write permissions (e.g., creating coupons). No refund capability—that stays manual.
For Gmail/outbound actions, everything goes through human-in-the-loop. The bot drafts responses and queues them for one-click approval. Nothing leaves the system without explicit confirmation.
OpenClaw logs every tool call with full context, so auditing is built-in. The general principle: read access is generous, write access is tight and gated.
It's less "keys to the kingdom" and more "keys to the lobby with a security desk."