Version 1.0.0 preview
This version is being prepared for release. Public availability is pending.
Reads webpages, selected text, and PDFs with ten local English Kokoro voices, synchronized highlighting, transcript navigation, saved reading position, and playback from 0.5× to 3×. English scanned PDFs use local OCR.
Optional OmniVoice narration adds experimental WebGPU voices and language, pitch, age, tempo, gender, and whisper settings.
Voices and privacy
Missing voice files download from Hugging Face when you prepare or use a voice. Speech runs on your device. Successfully cached files can be reused offline for the same voice and processing mode. Clearing the cache can require another download. No account is required.