Professional Text-to-Speech.
Turn any text into natural, expressive speech. 100% local. 100% private.
macOS • Apple Silicon • Works Offline
See Cast in Action
318+ voices, voice cloning, and multi-track editor — all running locally on your Mac.
318+
Built-in Voices
17
Languages
100%
On-Device
$19.99
Intro Offer
See It in Action
Professional text-to-speech with a beautiful, intuitive interface.
Choose from 318+ built-in voices or create your own
Everything You Need
A complete text-to-speech studio for podcasters, content creators, filmmakers, and professionals.
318+ Built-in Voices
Male, female, and neutral voices across different ages and styles. Each voice carefully selected for clarity and naturalness.
Voice Cloning
Create custom voices from just 5-30 seconds of audio. Clone your own voice or any voice you have permission to use.
Multi-Voice Scripts
Create conversations, podcasts, and audiodramas with up to 4 different voices. Color-coded for easy identification.
Multi-Track Editor
Professional timeline-based editor. Layer voices, music, and sound effects. Split, trim, and mix to perfection.
Natural Prosody
Human-like rhythm, stress, and intonation. Control expression level and add natural sounds like [laugh], [sigh], [hmm].
17 Languages
English, German, Spanish, French, Italian, Japanese, Korean, Chinese, and more with dedicated language processing.
Built For Creators
Content Creators
- YouTube narration
- Podcast intros & outros
- Social media audio
- Course voiceovers
Business
- Training videos
- Presentation narration
- Internal communications
- Prototype demos
Creative
- Audiobook narration
- Character voices for games
- Video dialogue
- Audio drama production
Accessibility
- Text-to-speech for reading
- Document narration
- Custom voice for personal use
- Learning assistance
Your Voice. Your Mac. Your Privacy.
Unlike cloud-based TTS services, Cast runs entirely on your Mac. Your text and voice data never leave your device.
Text Processing
100% on-device
Voice Synthesis
100% on-device
Voice Cloning
100% on-device
Data Collection
None
Simple Pricing
One-time purchase. No subscription. No credits.
Free
$0
- • 10 text-to-speech generations
- • 2 custom cloned voices
- • 10 exports per day
- • All 318+ built-in voices
Premium
$19.99 intro offer
- • Unlimited generations
- • Unlimited voice clones
- • Unlimited exports
- • All current and future features
No monthly fees. No per-word costs. Pay once, use forever.
Technical Details
System Requirements
- • macOS (Apple Silicon optimized)
- • ~720MB - 1.2GB for TTS models
- • ~1.5GB memory during synthesis
Export Formats
- • WAV - Professional editing, highest quality
- • M4A - Best quality/size ratio
- • MP3 - Widest compatibility