Artifacts

Transcribes or translates speech from an audio file, URL or microphone with Whisper running inside the browser tab.

Streams live microphone audio through Whisper on the GPU in your browser and prints the words as you speak.

Transcribes a recording in the browser and labels which speaker said each segment.

WebGPU-accelerated Whisper that turns microphone or file audio into text locally in the browser.

Speech recognition with the smaller Distil-Whisper model, executed locally in the browser.

Open-weight text-to-speech that downloads the model once and runs in your browser.

Multilingual text-to-speech with voice cloning that runs entirely in the browser on CPU.

Whisper speech recognition running on the Ratchet WebGPU runtime inside the browser.

Whisper transcription compiled to WebAssembly with Rust Candle, running in the page.

IBM Granite speech recognition running locally through WebGPU in the browser.

Semantic search over audio clips powered by Transformers.js models running in the browser.

Piper neural text-to-speech running in the browser with ONNX, with language, voice and speed controls.

Transcribes audio with Whisper in a Gradio-Lite page, with Transformers.js doing the inference locally.

Real-time text-to-speech with the Soprano model running via ONNX in the page.

Live Arabic speech transcription from the microphone with Voxtral Mini on WebGPU.

Reads text aloud with a speech model executed in the browser through Gradio-Lite.

Voice-activity detection plus Chinese speech recognition running as WebAssembly in the browser.

Persian text-to-speech that runs through ONNX in the browser.