About this app

SpeakerLens is a powerful macOS app that uses deep learning to identify and verify speakers by their voice characteristics — all running entirely on your Mac with Apple Silicon. No cloud services, no internet required for voice analysis. How it works: 1. Enroll speakers — select an audio file and give the speaker a name 2. The app extracts a 256-dimension voice embedding using the WeSpeaker ResNet293 model via CoreML 3. To identify an unknown voice, drop or select a test audio file 4. Tap "Match" — the app compares the test voice against your voiceprint database using cosine similarity Key Features: • AI-powered speaker identification using WeSpeaker ResNet293 (on-device CoreML) • Voiceprint enrollment — build your personal speaker database from audio files • Voiceprint matching — identify unknown speakers against enrolled voiceprints • Drag & drop audio files for quick testing • Audio preview for both enrolled and test samples • Similarity scores with color-coded confidence badges (green >80%, orange 30–80%) • Supports WAV, MP3, M4A, FLAC, AAC, AIFF, CAF, and all macOS AVFoundation formats • Beautiful dark & light mode interface with Material 3 design • Fully localized in 7 languages: English, Chinese, Japanese, Korean, German, Spanish, French Use Cases: • Podcast & media — identify speakers across episodes • Voice verification — confirm identity by voice • Audio/video production — tag speakers in recordings • Call center training — match agent voices • Forensic & research — voiceprint comparison analysis Why SpeakerLens? Most speaker identification tools require uploading audio to the cloud and charge monthly subscriptions. SpeakerLens runs the AI model entirely on your Mac — your voice data and voiceprints stay completely private. Pay once, use forever. 7-Day Free Trial: Try SpeakerLens with full functionality for 7 days. After the trial, unlock unlimited voiceprint enrollment and matching with a one-time purchase — no subscriptions, no recurring fees. 100% Private: SpeakerLens processes all audio entirely on your Mac using Apple Silicon (CoreML). No audio recordings, voiceprints, or usage patterns are ever sent to external servers. Your voice data stays yours.

Latest release

What’s New

Version 1.0.4 Jun 17, 2026

bug fixing

Audience growth

Ratings growth

Steady

7-day gain +0

Ratings / day 0.0

30-day gain +0

US rating-count history

0 ratings

Baseline captured. Growth appears after the crawler observes a changed rating count.

Momentum comes from crawler snapshots for the tracked storefront. “Viral growth signal” means unusually fast recent rating gains; it is an indicator, not download data.

Price tracking