Keep your media local
Your recording is processed in your browser, not sent to a transcription server.
LOCAL PROCESSING · REAL CONTROL
Turn audio and video into editable text and subtitles. English, French and Arabic, processed on your own device.
Free to use. No account needed. Media stays on your device. Models download separately.
Best supported on current desktop Chrome. Codec support, speed and memory vary by browser and device. Mobile transcription is not guaranteed.
Interviews, meetings, lectures, and everything worth keeping.
Audio and video files are processed locally in your browser.
MP3, WAV, M4A, AAC, FLAC, OGG, OPUS, MP4, MOV, WebM, MKV, M4V and 3GP with supported audio codecs. Files are checked locally. AVI, WMA and MPEG/MPG program streams are not supported. Codec support varies by browser.
Transcription runs locally in your browser. Your audio and video are not uploaded to our servers.
Models download on first use. A loaded model is reused; change model or processing mode to release it.
Choose a recording to get started.
Progress will appear here.Document edits apply to copied text and TXT. Subtitles and JSON preserve the original timed transcription.
Timestamps are model estimates. Total RAM and GPU memory are not available to this page; use your browser’s task manager.
Arabic uses a dedicated model with about 1.33 GB of weights and CPU/WASM processing. The first run may take several minutes. General model and GPU choices do not change the Arabic model.
Your recording is processed in your browser, not sent to a transcription server.
English, French and Arabic transcription. Auto Detect uses the beginning of the recording.
Copy text or download TXT, SRT, VTT and JSON. No account required.
Open an audio or video file. We check its audio track in your browser.
Choose the spoken language or Auto Detect. Allow the required model to load.
Listen back to important passages, edit your text and download the format you need.
MP3, PCM WAV, MP4/AAC, M4A/AAC, MOV/AAC, WebM/Opus, OGG and FLAC are among the tested combinations in desktop Chrome. A container extension alone does not guarantee codec support.
Turn recordings into an editable transcript on your own device. Review your words and export text without uploading the audio.
Read what was said in a video. Extract and transcribe its audio locally, then edit or download the result.
Edit a readable transcript, review original subtitle timings, or keep structured JSON. Text edits and corrections apply to Copy Text and TXT; SRT, VTT and JSON keep the original timed transcription.
Create original-language subtitle files from audio or video, with estimated start and end times.
Create an SRT subtitle file from a recording, using the original transcription and its timestamps.
Generate a WebVTT file for a web-video caption track from your audio or video recording.
Speech recognition and text checking run locally. The website and model files still need network access. Hosting and model providers can receive ordinary connection information; they do not receive your recording through this tool.
Understand local processingMake interviews easier to review, turn lectures into study notes, find passages in podcasts, or prepare subtitle files for your videos. Always review names, numbers and important quotations against the recording.
Turn an exported voice memo into editable text. Open a local M4A or other supported recording, transcribe in your browser and download TXT.
Make a readable transcript of a lecture recording. Review terminology and references, then save text or original timed segments for study.
Transcribe a recorded interview locally, check quotations against the audio and keep readable text separate from the original timed segments.
Create a transcript of a local podcast episode, review guest names and quotations, then download text or a subtitle track for the final recording.
Transcribe English audio or video locally, then review the text with optional English writing checks.
Turn spoken French into French text. Review accents, agreements and punctuation with local French checking.
Transcribe spoken Arabic into Arabic text using the dedicated local Arabic recognition model.
Choose the Arabic model, prepare a clear recording and review dialects, names and subtitle timing without uploading your media.
A step-by-step guide to local transcription: check the audio track, choose a language, review the words and export text or subtitles.
Understand local media processing, model downloads, browser storage and offline limits before transcribing a private recording.
Check French names, negation, homophones and agreements against the recording, then review local writing suggestions and export the right version.
Prepare an audio or video file, choose a language, review recognition errors and export the right version of your transcript.
Understand the practical difference between SRT and WebVTT, choose an export and check captions before publishing.
No. The browser reads and transcribes it locally. Website assets and model downloads use the network separately.
A model already loaded in an open page can be reused offline. Reloading, switching models or clearing storage may require network access.
No. Copy Text and TXT use the selected document version. SRT, VTT and JSON keep the original timed transcription.