AI Text to Speech 1.0.14 | Portable

Multimedia
20 April 2026, 07:23

AI Text to Speech is an offline Windows desktop AI text-to-speech app for fast local voice generation. Paste your script, choose a model and voice, generate speech, preview the result, and export WAV files.

AI TTS is built for creators, students, and professionals who want a fast, repeatable desktop TTS workflow.

Features

Local AI synthesis workflow (no cloud API key required)
Up to 10,000 characters per generation
Automatic chunking for long scripts to keep generation stable
Speed control from 0.50x to 1.50x
Preview player with play/pause, seek, and preview history navigation
Manual export mode: choose save location when exporting
Auto export mode: save directly to your configured output folder
Inference hardware preference in settings (Auto / CPU / GPU)
Dark and light themes
In-app logs, notices, and license references
Built-in settings for defaults and export behavior

Key Features

Offline-first Windows AI text-to-speech workflow
Two built-in model engines: Kokoro-82M and KittenTTS
Model, language, and voice selection directly in the main screen
Multilingual speech generation with Auto-detect support
Supports English (US), English (UK), Spanish, French, Italian, Hindi, Brazilian Portuguese, and Mandarin Chinese
Up to 10,000 characters with stable chunked generation
Speed control (0.50x to 1.50x)
Preview player with seek and preview history
Manual export (Save dialog) and Auto export (folder-based)
WAV export for production use
Inference hardware preference: Auto, CPU, or GPU
In-app logs, notices, and license references

Screenshots