“transcription”

Transcribes piano audio into MIDI notes in the browser using the Onsets and Frames model.

Transcribes a video with Whisper and adds a short AI-written summary.

Paste a YouTube link to get a Whisper transcript of the video's audio.

Transcribes and translates a video's speech, producing subtitles.

Real-time captions of your microphone using the Moonshine ONNX model.

Converts music audio into MIDI notes.

Turns JSON audio transcripts with speakers and timestamps into Markdown.

HTML5 player and text pane for transcribing interviews, with keyboard shortcuts to control audio playback.

Multilingual speech recognition from audio files or the microphone.

NVIDIA Nemotron speech-to-text demo.

Transcribes uploaded audio with Whisper.

Transcribes audio and attributes each passage to a speaker.

Speech-to-text for Arabic audio.

Quick Whisper Turbo transcription of audio files.

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

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

Fast Whisper transcription for audio or video files, with subtitle output and a translate option.

A voice assistant you talk to through your microphone, with a choice of voice and language and a written transcript.

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

Step through transcription and translation to build a protein from a gene.

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

Hosted Whisper demo that transcribes or translates microphone input and uploaded audio.

English speech recognition with NVIDIA Parakeet, returning text and timestamps.

Transcribes audio files or microphone input with the Whisper large-v3 model.