Free Audio to Text Converter - Private Transcription and Subtitles in Your Browser

What it does: turns audio and video into text and subtitles. Drop a file or record from the microphone, and the transcript appears as it is recognized, with timestamps. Download it as TXT, SRT, VTT, or JSON.

Who it is for: creators, students, journalists, and podcasters who need a transcript or subtitles now, site owners who want their own free transcription page, and developers who want speech recognition in the browser.

What you get: use it free in the live preview above, or take the whole tool: a one-page site for any static host with no server, no database, and no API keys, the Whisper speech model running in the visitor's browser, reusable modules for audio decoding and subtitle formats, tests, and HTML documentation.

What you do: drop an audio or video file. The first time, the browser downloads the speech model and keeps it. To host it yourself, upload the audio-to-text folder to any static host.

Features

• Private by design: the file is decoded and transcribed on the device and never uploaded. No sign-up, no limits, no ads.
• Audio and video files: MP3, WAV, M4A, AAC, OGG, Opus, FLAC, WebM, MP4, and MOV, or record from the microphone.
• 99 languages, detected automatically from the first 30 seconds or chosen from the list, and translation into English.
• Two models: Fast (41 MB) for clear speech and Accurate (77 MB) for accents and noise. Downloaded once, then cached, so it also works offline.
• Long recordings in 30-second parts with live text and a progress bar, and Cancel.
• Export as TXT (with or without timestamps), SRT and VTT subtitles, or JSON segments.
• Clear messages for files that are not audio, silent audio, a blocked microphone, and a failed model download.
• Settings in one file: models, default language, and self-hosting the model and runtime.

Screenshots