clir Hearing vs Demixr

clir Hearing is an iOS app that uses on-device processing to make speech clearer through headphones or hearing devices. Place an iPhone near a conversation or hold it, then open the app; it detects speech and removes background noise in real time. Clear Speech mode applies AI noise removal, while Original mode provides natural, gently amplified sound. Listed compatible devices include AirPods, Made-for-iPhone hearing aids, most Bluetooth headphones, and cochlear implants. Stated latency is 8 ms with wired audio and 98 ms with wireless audio. The app works without internet and requires no account. Audio stays on the device: conversations are not uploaded, stored, or used for training. Suggested situations include restaurants, family gatherings, meetings, television, and calls. First sessions are free without sign-up, with in-app purchases afterward. Monthly access costs $12.99 a month; yearly access costs $59.99 a year. It requires iOS 15.0 or later and is not a medical device.

Demixr is a web service for processing audio, with tools for separating vocals and instruments, removing reverb, marking speech, and analyzing BPM and key. Its Pro 1.5 vocal separation has Voice mode for complex mixes, live recordings, or speech over music, and Music mode for songs and covers or separating vocals from accompaniment. A separate stem tool uses Demucs to split music into vocals, drums, bass, and other parts. For dereverb, Demixr recommends isolating vocals first; applying the effect to a mixed track can cause artifacts or distortion. VAD provides editable speech-segment markers and batch export, though detection may be inaccurate with quiet vocals or noisy recordings. BPM analysis includes tempo, key, and Camelot values, with optional tap-to-sync. The free plan costs nothing and includes 10 minutes of audio monthly, a 10 MB upload limit, two VAD uses, queued processing, and no WAV downloads. Paid one-time plans start at $4/mo, without automatic renewal. Uploads and outputs are deleted within 24 hours by default.