Offline text-to-speech for Mac with local voice cloning and no cloud uploads
Voice AI for how Singapore speaks
Stage
Not given
MVP
Founded
Not given
Not given
Based in
Not given
US
Pricing model
Freemium
Contact for pricing
Pricing
Free: $0 (up to 1,000 characters per synthesis, single file export, one custom voice, limited background processing). Pro Monthly: $6.99. Pro Yearly: $29.99. Pro Lifetime: $49.99 (unlimited generations up to 20,000 characters, unlimited custom voices, unlimited batch exports, unlimited background pr
Not given
Key features
185 English voices with various accents
Local voice cloning from 6-10 second audio samples
Batch export to MP3, WAV, AIFF, and M4A
Background queue for multiple synthesis jobs
Import from TXT, Markdown, DOCX and more file formats
Project workflow for long-form content and PDFs
Light and dark mode support
Uses less than 2GB of RAM
Streaming speech-to-text for Singlish, English and Mandarin
Natural turn-taking that distinguishes pauses from completion and handles interruptions
Tool calling to pick actions and call custom functions
Grounded responses using instructions and tool results
Local voices in English and Mandarin with natural acknowledgements
Text-to-speech API
Realtime session playground in browser
Python and TypeScript SDKs coming soon
Websocket API for streaming audio
What makes it different
Completely offline operation with no cloud uploads or data transmission
One-time purchase option with lifetime access
MIT-licensed Chatterbox Turbo model with expressive output
Privacy-focused design built for creators who value control
Built on models trained specifically on local Southeast Asian speech patterns, accents and languages
True real-time architecture with streaming at every layer for immediate responsiveness
Privacy-first design with no call audio stored after sessions end
Handles mixed-language conversations seamlessly within single calls
Spokio
Tavia Labs