AIVoiceSeparator vs clir Hearing

AIVoiceSeparator separates songs into vocal and instrumental stems for backing tracks or clean vocals. Its Studio pipeline combines BS-Roformer, Mel-Roformer, and MDX23C, then applies EBU-R128 loudness normalization. The maker reports an SDR of 12.97 dB and says this is roughly 3 dB above the open Demucs baseline. The web app accepts audio and video files up to 100 MB and 20 minutes in formats including MP3, WAV, M4A, FLAC, OGG, WebM, Opus, and MP4/MOV. You can submit YouTube or SoundCloud links; TikTok clips must be saved and uploaded. Optional Whisper transcription returns SRT, LRC, and TXT files and adds about 30 seconds to processing. A REST API accepts a URL or upload and returns both stems. The free plan allows three songs per month when signed in; pay-as-you-go credits cost $0.50. The maker says uploads and results are deleted within 24 hours and audio is not used to train AI models.

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.