Generate timed subtitles from speech in a local video. Review the captions alongside playback, correct text and timing, then download SRT or VTT.
Drop a video here or click to select
The browser previews supported video formats locally.
Auto-detect is the default. Select a language if detection is inaccurate.
Standard is faster and uses less memory. Enhanced may improve recognition but needs a larger download, more memory and more time.
Leave the end blank to process to the end. Regenerating a range replaces overlapping cues and keeps the others.
Recognition resources download on first use, then reuse the browser cache when available.
Generate subtitles from speech in your local media file. Once complete, captions follow playback.
Drop an SRT or VTT file here or click to select
Import SRT or VTT. All cues are kept.
The project saves edits, subtitles and settings locally, without the media. Reselect the same original file to restore; its complete contents are checked.
Media files are processed in your browser and are not uploaded to a server.
Add audio or video files and process them one at a time using each file’s first audio track.
Recognition resources download on first use, then reuse the browser cache when available.
Language, recognition mode and speaker labels apply to every file in the next run. Changing settings keeps completed results; failed or cancelled files can be retried with the current settings.
The ZIP includes SRT and VTT for successful files only. Duplicate names receive a number.
No files in the queue.
Create captions for interviews, lessons, presentations and recorded clips. Generation finishes before playback displays the new subtitles; it does not transcribe live. The downloaded subtitle file is separate from your original video.
Select your video, generate the subtitles and review them in the editor. Click Export SRT to download text with start and end timestamps. Export VTT creates a WebVTT file instead.
No. Audio extraction, recognition and editing happen in your browser. The first generation downloads the processing resources; later runs can reuse the browser cache.
Automatic detection is the default. Under Settings, you can choose the spoken language explicitly. Recognition transcribes the speech in its original language; it does not translate captions.
Yes. Recognition completes first and preserves the video timeline. Captions then follow playback and seeking. You can edit individual times or shift all captions if needed.
Use clear speech and select the correct language. Enhanced mode can improve recognition but uses more memory and time. Noise, music and overlapping speech can cause errors, so review the captions before exporting.
Yes. Open the batch panel and add audio or video files. They are processed one at a time using the first audio track. Download each successful result as SRT or VTT, or download a ZIP with both formats. Duplicate filenames receive a number.
A failed file does not stop the remaining queue. Retry failed or cancelled files with the current settings. Settings apply to the next run and completed results are kept. Keep this page open while processing; phones may pause or stop work when the page goes into the background.
Format and beautify Java, Python, JavaScript, JSON, HTML and more; adjust indentation, spacing and line breaks.
Trim, join or split recordings, remove silence or noise, and adjust volume, speed, pitch or channels.
Open and edit CSV or Excel sheets, format tabular text, and convert CSV to Excel or SQL.
Write and preview Markdown, render Mermaid diagrams, and convert Markdown, HTML and tables between formats.
Compare passages, count words and keywords, sort or replace lines, and view DOCX text.
Look up Chinese meanings, synonyms and antonyms, or find IPA pronunciations in multiple languages.
Convert between MP3, WAV, FLAC and more, play audio or raw PCM, and inspect or edit audio metadata.
Inspect, compare and validate JSON; test JSONPath expressions, or convert data to CSV, YAML and XML.
Transcribe audio to text, generate speech from text, or record your voice in the browser.
Convert and compress video, trim or join clips, resize frames, and extract audio.
Play local or streaming video, record your screen or camera, and use your camera as an online mirror.
Compress or merge PDFs, split and rearrange pages, convert pages to images, and view or compare documents.
Convert image formats, resize or crop photos, compress files, compare pictures, and extract text with OCR.
Capture and beautify screenshots, turn text into images or GIFs, draw on a whiteboard, and create word clouds or favicons.
Edit SRT or VTT captions with a video preview, shift timing, convert formats, and manage subtitle tracks.
Open ZIP, 7Z, RAR or TAR files, extract selected contents, and create new archives with optional ZIP/7Z passwords.
Encode and decode Base64 or Base32, escape URLs, HTML and Unicode text, and inspect JWT contents.
Convert number bases and values between binary, decimal and hex; turn numbers into words or text into binary.
Work out percentages and fractions, summarize statistics, and calculate grades, discounts or aspect ratios.
Show an online clock, run a countdown or stopwatch, and calculate dates, ages or time-zone differences.
Check your IP and IPv6 connection, inspect HTTP requests or HAR files, and calculate CIDR address ranges.
Convert length, weight, temperature, data storage and other units.
Convert HEX, RGB and HSL values, extract colors from an image, check contrast, or test your display with solid colors.
Generate and scan QR codes or barcodes, including QR codes for links and Wi-Fi networks.
Generate hashes, UUIDs and passwords, test regular expressions, create URL slugs and check file permissions.
Check screen resolution and refresh rate, measure with a screen ruler, test keys, or read from a teleprompter.
2048, Minesweeper, Sudoku, Gomoku, Tank Battle