Transcribe Audio to Text with AI
Audio to Text in Three Steps
Upload a recording or video
MP3, WAV, M4A, MP4, MOV and more, up to 2 hours. Your browser turns it into a compact audio file first, so videos never leave your device.
Get a transcript with speakers
The language is detected for you. Every sentence is timed to the word, and each voice is labeled Speaker 1, Speaker 2 and so on.
Edit, translate and export
Click a sentence to hear it, fix a word and rename the speakers. Translate it to read both languages together, then download a transcript, plain text, SRT subtitles or VTT captions.
A Transcript You Can Check, Not Just Read
Translate it and read both languages
Know who said what
Click any sentence to hear it
Fix words right in the transcript
Transcripts and subtitles, free to export
Long recordings, video files, 30 languages
From Recordings to Text You Can Use
Anything with people talking: one file, one transcript, ready to quote, search or subtitle.
Interviews
Turn recorded interviews into text you can quote, with each person labeled and every line linked back to the audio. Interviewed someone in another language? Translate it and read both.
Meetings and calls
Upload the recording and get notes-ready text that shows who said what, instead of replaying the whole call.
Lectures and classes
Transcribe lectures to study from, search for the part you missed, and jump straight to it.
Podcasts
Make show notes, pull quotes and publish an accessible transcript for every episode.
Video subtitles
Get SRT or VTT captions for YouTube, social clips or your video editor, from the video file itself. Add a translation for bilingual subtitles.
Voice memos
Turn ideas and notes you recorded on your phone into text you can edit and share.
More Tools for Your Recordings
Remove background music and noise from a recording before you transcribe it.
Transcribing a song? Get lyrics synced to the music as LRC or SRT.
Turn your edited text back into natural speech with 30 voices.
Clean up hiss, hum and room noise in voice recordings.
Convert between MP3, WAV, M4A and other formats in your browser.
Pull the lyrics out of any song as text you can copy.
Audio to Text Questions
Upload an audio or video file, leave Identify speakers on if more than one person is talking, and press Transcribe. When it's done, open the transcript to play it back, fix any words and export it. You can leave the page while it works; you'll be notified when it's ready.
Lacuna is free to start. Free accounts get 120 credits every month, enough for about 24 minutes of audio. Transcription costs 5 credits per minute, rounded up, and every export (TXT, SRT and VTT) is free.
Most audio and video formats, including MP3, WAV, M4A, AAC, FLAC, OGG, Opus, WebM, MP4 and MOV, up to 2 hours long. Your browser converts the file to compact audio before upload; for a video, only the sound is sent.
30 languages, including English, Spanish, Portuguese, French, German, Japanese, Korean and Chinese. The language is detected automatically, so there's nothing to set. Once it's transcribed, you can translate it into 18 languages.
Yes. Open a transcript, choose Translate and pick one of 18 languages, from English, Spanish and French to Japanese, Korean and Chinese. Each sentence of the original shows its translation right below it, or you can show the translation alone. Each language costs 2 credits per minute of audio, and switching between languages you've already translated is free. Copy and export follow what you see, so you can download bilingual SRT or VTT subtitles.
Yes. With Identify speakers on, the transcript is split by voice and labeled Speaker 1, Speaker 2 and so on. Click a name to rename that speaker everywhere. It works best when people don't talk over each other.
Yes. Switch to Edit and click any sentence to change it. Edits save automatically, you can restore any sentence to the original, and every export uses your edited version.
Transcribe the file, choose Export and pick SRT or VTT. Captions are split into short lines, at most two per caption and a few seconds each, and the VTT file keeps speaker names. With a translation open in Bilingual view, each caption shows the original line with its translation underneath.
You can, but lyrics come out better in the LRC generator: it separates the vocals from the music first and times every word to the beat.
Turn Your Next Recording into Text
Upload audio or video and get a timed transcript with speaker labels, ready to translate. Free accounts get about 24 minutes every month.