Generate speech from text using local AI models. Download as WAV. Runs entirely in your browser — private and free.
Convert text to natural-sounding speech using local AI models powered by HuggingFace Transformers.js and ONNX — everything runs 100% in your browser, no server, no API key. Choose from English, French, German, or Spanish MMS-TTS models (each ~45 MB, cached after first download), type or paste your text, then generate speech and download it as a WAV audio file. Perfect for creating voice-overs, accessibility audio, or offline TTS with full privacy.
Chat with an AI model that runs privately in your browser — fully offline after download.
Choose a language / model
Powered by HuggingFace Transformers.js with ONNX runtime. All inference runs locally in your browser — no data is sent to any server. Models are cached after first download.