Offline TTS provides a private browser‑first AI audio toolkit offering free text‑to‑speech, speech‑to‑text, subtitle generation, and ebook/audio conversion without sign‑up or API keys. All core tools run locally in the browser, keeping data on‑device and enabling unlimited usage.

The platform bundles several engines: Kokoro (the primary free TTS with 54 voices across 9 languages and 8 expressions), Kitten (a lightweight 25‑voice TTS for fast drafts), Piper (CPU‑friendly synthesis supporting 5 languages), Supertonic (multilingual TTS with style presets for English, Spanish, Portuguese, French, Korean, and 99 languages), and Whisper (robust audio‑to‑text transcription that exports TXT, SRT, VTT and works offline after model download). Users can export WAV/MP3 from voice workflows.

Use cases span creators needing narration and subtitles, accessibility conversion of text and media, study‑focused document‑to‑audio listening, and private research or team transcription where privacy outweighs cloud convenience. The service remains free, with optional commercial use subject to upstream model terms. To begin, select the desired audio workflow—voice generation, transcription, subtitle cleanup, or EPUB/PDF/TXT listening—directly from the tools directory.