Load content
Import Content
Drop files, paste URL, or click to browse
New here? Find free public-domain books at Standard Ebooks or Project Gutenberg.
No book loaded. Drop a file above, paste text, or open your Library.
Drop files, paste URL, or click to browse
New here? Find free public-domain books at Standard Ebooks or Project Gutenberg.
No book loaded. Drop a file above, paste text, or open your Library.
Please wait while we prepare your book
Max file size: 50MB
Uploading...
Controls voice variation and creativity (Chatterbox only)
Voices will load automatically when you enter your API key
Models will load automatically when you enter your API key
Uses Kokoro-FastAPI server. Click ↻ to load voices from server.
MP3 recommended for best iOS compatibility
Models will load automatically when you enter your API key
Uses your browser's built-in speech synthesis. Click ↻ if voices don't load.
Speed of speech (0.1 = very slow, 2.0 = very fast)
Voice pitch (0.0 = lowest, 2.0 = highest)
Speech volume (0.0 = silent, 1.0 = full volume)
iOS Native TTS uses the system speech synthesis for the best performance and battery life on iOS devices.
Speed of speech (0.1 = very slow, 2.0 = very fast)
Voice pitch (0.5 = low, 2.0 = high)
Voice volume (0.1 = very quiet, 1.0 = full volume)
Voices available through iOS TTS. Install Enhanced and Premium voices for highest quality
Opens Settings → Accessibility → Spoken Content → Voices
To download additional voices or manage voice settings:
Go to iOS Settings:
Settings → General → Accessibility → Spoken Content → Voices
Here you can download premium and enhanced voices, adjust speech rate, and configure voice settings.
Used by: Chatterbox, Kokoro, OpenAI, Google Cloud (not ElevenLabs)
Number of audio chunks to buffer ahead for smooth playback
Optional, for self-hosting. URL imports try a direct fetch first, then the built-in same-origin proxy. Only set this if you host VoiceWeaver without that proxy — point it at your own CORS proxy (e.g. a Cloudflare Worker).
Auto mode follows your operating system's theme preference
Visually indicate short and long chunks with color coding
Choose how your API keys are stored for security vs convenience:
Runs comprehensive iOS MediaSession diagnostic and saves results to a log file. Check iOS Files app → VoiceWeaver → Documents for the debug log.
Toggles a persistent MediaSession test. When active, check iOS Control Center to see Now Playing info and test controls.
VoiceWeaver is an intelligent text-to-speech reader that transforms your books, documents, and articles into immersive audio experiences. Upload files or paste text to listen with high-quality AI voices while following along with synchronized highlighting.
Uses your device's built-in voices. Works offline, no setup required.
Premium voices with natural speech patterns and emotions.
Run your own TTS server for complete privacy and control.
For the best mobile experience, add VoiceWeaver to your home screen:
This creates an app-like experience with faster loading and easier access!
VoiceWeaver stores all your settings, API keys, and library locally in your browser. This data will be permanently lost if you:
💾 Backup Recommendation: Export your settings and library regularly using the export functions in Settings → Maintenance to prevent data loss.
What stays on your device:
What is sent to third-party services:
VoiceWeaver uses a bring-your-own-key model. We never see, store, or have access to your API keys. Keys are encrypted client-side and sent directly from your browser to the provider.
Paste or type content below. Supports plain text, HTML, and Markdown.
You have a saved reading session:
Enter a URL to import web content into your library:
Supports articles, blog posts, and other web content