Audio to PDF
Transcribe spoken audio into a readable PDF transcript.
The browser's SpeechRecognition API is built for live microphone input, not transcribing an arbitrary uploaded audio file, and a client-side speech-to-text model (Whisper-class) would mean a 100MB+ download for every user. This tool sends the audio to a server-side transcription API instead. See docs/DECISIONS.md 2026-09-03.
Choose PDF files
or drag and drop here