Voice & Image to Text
FreeAI DrivenDictate or record speech, or read text out of an image with OCR.
Live dictation uses your browser's built-in speech recognition (Chrome, Edge, Safari), which may send audio to the browser vendor. Audio-file transcription needs OPENAI_API_KEY and image OCR needs ANTHROPIC_API_KEY on the server.
This browser can't record audio (or the page isn't served over HTTPS).
Or upload an audio file
MP3, WAV, M4A, WebM or OGG, up to 24 MB
Extracted text
No text yet
Record or upload audio to begin.