About this app
Utterly is a powerful macOS app that lets you clone any voice from a short audio sample, create brand-new voices from text descriptions, and generate natural, expressive speech — all running entirely on your Mac with Apple Silicon. No cloud services, no internet required after setup. **Two Ways to Create Voices:** • From Audio (Voice Cloning) — Drop a 3–5 second clean voice recording and type what's being said. The AI extracts the voice characteristics and saves them to your library. • From Prompt (AI Voice Generation) — Simply describe the voice you want in natural language (e.g. "A warm, gentle female voice with a soothing tone"). The AI generates a matching voice profile — no audio sample needed. **How it works:** 1. Download the AI model once (~3.4 GB, one-time setup) 2. Add a voice — clone from audio or generate from a text description 3. Type any text and generate speech in your chosen voice **Three Powerful Modes:** • Quick TTS — Type or paste any amount of text and instantly generate speech. Long text is automatically split into optimal segments and merged into a single audio file. Perfect for everything from quick voiceovers to full audiobook narrations. • Batch Processing — Process multiple text items at once. Import .txt files or paste a list — each item becomes a separate audio clip. Great for producing content at scale. • Multi-Voice Dialogue — Create multi-character conversations. Write a script with role labels like [Narrator], [Alice], [Bob], assign a voice to each role, and generate the full dialogue with seamless transitions. **Key Features:** • Clone any voice from just 3–5 seconds of audio • Create new voices from text descriptions — no audio needed • Generate natural, expressive speech in multiple languages • Automatic language detection (Chinese, English, Japanese, Korean, French, German, Spanish) • Build a reusable voice library with unlimited profiles • Show in Finder — quickly locate generated audio files • Adjustable playback speed for generated audio • Beautiful dark & light mode interface • Fully localized in 7 languages **Supported Audio Formats:** WAV, MP3, M4A, FLAC, OGG, AAC, AIFF, OPUS **Why Utterly?** Most voice cloning tools require uploading your audio to the cloud and charge monthly subscriptions. Utterly runs the AI model entirely on your Mac — your voice data never leaves your device. Pay once, use forever. **Create Your First Voice Free:** Get started right away — create your first voice at no cost. Want more? Unlock unlimited voice creation with a one-time purchase — no subscriptions, no recurring fees. **100% Private:** Utterly processes all audio entirely on your Mac using Apple Silicon. No voice samples, text input, or generated speech is ever sent to external servers. Your voice stays yours.
Latest release
What’s New
bug fixing and new IAP mechanism
Audience growth
Ratings growth
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
Price intelligence
First snapshot captured. The trend line starts after the next crawler price observation.
- First observed Aug 7, 2026 · 10:26 PM Free