OfflineTTS
Converts text to speech and speech to text directly in the browser, with support for multiple TTS engines, transcription, subtitles, and document audio.
A browser-based text-to-speech and speech-to-text tool that converts text into natural-sounding audio and transcribes audio into text, solving the need for private, on-device voice processing without cloud uploads. It targets content creators, students, teams, and researchers who require privacy-focused audio workflows, including narration, transcription, and subtitle generation. The tool is positioned as a free, no-signup alternative to upload-first services, with all core processing running locally in the browser, and supports offline use after model download.
Key features
- Local TTS engines: Kokoro, Kitten, Piper, Supertonic
- Speech-to-text with Whisper (99 languages)
- Offline English TTS after model download
- WAV and MP3 audio downloads
- SRT and VTT subtitle exports
- EPUB, TXT, PDF document audio
- No signup or API key required
- Free to use with no per-character fees
- No social media activity within the last 30 days
GTM channels
- Blog
- Affiliate program
- API
ICP
- Content creators
- Students