Text-to-speech and speech-to-text — powered by your browser, fully private.
Uses a neural TTS model that runs in your browser. First download is ~40MB (cached for future use).
Speech Studio uses your browser's built-in Web Speech API — no audio is ever uploaded to a server. The Text to Speech tab lets you choose from all voices installed on your device, control speed and pitch, and watch word-by-word highlighting as it reads. The Speech to Text tab uses your microphone to transcribe speech in real-time, showing interim (unconfirmed) results as you speak. Speech recognition is available in Chrome, Edge, and other Chromium-based browsers.
Tune your guitar using your microphone. Visualize audio frequency data, detect pitches, and see hints to tune each string up or down.
Listen to sounds through your microphone and visualize their frequency and volume in three different styles: bars, waveform, and a circular view.
Count words, characters, sentences, and paragraphs instantly. Get reading time estimates and readability scores including Flesch-Kincaid and Gunning Fog index.
Extract frames from a video file and create an animated preview. Upload an MP4, WebM, or MOV file, set a time range and frame rate, then download individual frames as PNGs.
