What is this tool?
Voice to Text turns speech into text in English, Hindi, Tamil, Telugu, Malayalam, Kannada, Marathi, Bengali, Gujarati, Punjabi, Urdu and about 25 more languages. Upload an audio or video file (MP3, WAV, M4A, MP4, WebM, MOV and more, up to 30 minutes), record with your microphone, or use live dictation that types as you speak. Uploads and recordings are written down by OpenAI's Whisper large-v3-turbo model on Cloudflare Workers AI, with a timestamp for every line, so you can download .srt or .vtt subtitles as well as plain text. You can write the speech in its own language or straight into English, translate the result into Indian and world languages, and send it to Text to Voice to hear it in a natural male or female voice or to dub the video into another language. Nothing is stored.
How to Use
- Choose Upload audio or video, Record, or Live dictation.
- Pick the spoken language, or leave it on Detect automatically, and choose whether to write it in that language or in English.
- Press Transcribe. Long files are processed in parts with a progress bar; silent parts are skipped.
- Tick Show timestamps to see each line with its time and click a line to play from there.
- Copy the text or download it as .txt, .srt or .vtt, or translate it into another language.
- Press Read aloud or Dub the video to continue in Text to Voice with a natural voice.
Frequently Asked Questions
Which languages work best?
English, Hindi and most major world languages are very accurate. Tamil, Telugu, Malayalam, Kannada and other Indian languages work well on clear speech; choosing the language instead of automatic detection helps, and noisy or music-heavy audio lowers accuracy.
Is my audio stored?
No. The file is decoded in your browser and sent in short pieces to Wivrix's server, where Whisper on Cloudflare Workers AI writes it down; nothing is kept. Live dictation uses your browser's own speech service (Google in Chrome, Microsoft in Edge, Apple in Safari).
How much can I transcribe for free?
Up to 30 minutes per file and about an hour of audio a day per network, shared with the site's other AI tools. The allowance resets at 00:00 UTC.
Other tools
There are more calculators, converters and editors on Wivrix. If something is missing, tell us.