What transcription does
- Text in paragraphs with timecodes like [12:31], so a quote is easy to find and to go back to.
- A player next to the text. Click a word or a timecode to jump there; the current word is highlighted.
- Search and editing right on the page, and a Copy all button.
- Downloads: TXT with or without timecodes, DOCX for Word and Google Docs, SRT and VTT subtitles.
How to turn audio into text, step by step
- Upload audio or video: only the sound is taken from a video, and the file itself is not kept.
- Add names and terms if you like; it helps with spelling.
- Add names and terms from the recording to "Names and terms": the list is a hint for recognition.
- Press Transcribe. A long recording runs in the background: you can close the tab, we email you when it is ready, and the text appears under My transcripts.
Automatic SRT and VTT subtitles for a video
Subtitles are built from the same transcript with a time for every word, so you need no separate program. A line holds up to 42 characters, a cue has up to two lines, each cue stays on screen for 1 to 7 seconds and breaks at a pause rather than mid-phrase. Upload the SRT file to YouTube, or open SRT and VTT in a video editor.
If you fix a word, the paragraph keeps its timing and the words inside it are spread again, so the subtitles stay in sync.
Voice message to text
Voice messages saved from messengers usually come as OGG or OPUS, and phone voice memos as M4A or AMR. All of these are accepted as they are, no conversion needed. A short voice message fits into the free minutes even without an account: save it as a file, upload it and copy the text.
Meetings, interviews and lectures
Upload a recording of a call, a voice recorder or a video of a lecture. Text with timecodes is easy to turn into minutes, notes or an article: search finds every mention of a name, and a click on a phrase lets you listen to it before you quote it. After recognition the app writes a three-line brief, topics with timecodes and action items (who, what, when) if they were said.
Get the participants' consent before you record a meeting. Speaker labels are not in the first version: a dialogue comes as paragraphs split by pauses, and you can add names while editing.
Languages and formats
| What | Details |
|---|---|
| Languages | Russian |
| Audio | MP3, WAV, M4A, OGG, OPUS, FLAC, AAC, AMR, AIFF |
| Video | MP4, MOV, WEBM, MKV: only the sound is used |
| Downloads | TXT (with or without timecodes), DOCX, SRT, VTT |
What it costs
| What | Terms |
|---|---|
| Without an account | 5 minutes a day, the text is shown on screen; file downloads need sign-in |
| Signed in | 30 minutes a day, every download format |
| Daily reset | At midnight UTC; the app shows the minutes you have left before you start |
| Beyond the limit | For now transcription works within the daily limit. Later, beyond it, 1 token per started 30 minutes of recording; the summary, topics and action items are included |
Privacy
The audio is deleted right after transcription, the text is kept for 30 days, and Delete removes it at once. Recordings are processed on our own servers in Russia and are not used to train models. The brief, topics and action items are written by an AI service from the finished text: it receives only the transcript text, without the audio or account data.
Tips for a cleaner transcript
- Music under the voice makes recognition harder. Split the voice from a song first with the vocal remover.
- Room echo swallows words: remove the echo before you transcribe.
- Need only a part? Cut it out with the audio cutter and save your minutes.
- Rare names and terms are best added to the list before you start.
Related tools
Questions and answers
Is transcription free?
Yes, within a daily limit: 30 minutes signed in and 5 minutes without an account. The app shows what is left before you start, and the limit resets at midnight UTC. Later, beyond the limit, 1 token per started 30 minutes of recording.
Can I make subtitles for a video?
Yes. Upload the video and after transcription download SRT or VTT: up to two lines of 42 characters, each cue on screen for 1 to 7 seconds.
How do I turn a voice message into text?
Save the voice message as a file (OGG or OPUS from a messenger, M4A or AMR from a recorder), upload it and copy the text. A short message fits into the free minutes without an account.
Which language is supported?
Russian. There is no language to choose.
Does it separate speakers?
Not in the first version. A dialogue comes as paragraphs split by pauses, with timecodes, and you can add names while editing.
What happens to my recording?
The audio is deleted right after transcription. The text is kept for 30 days, and Delete removes it at once. Recordings are not used to train models. For the brief, topics and action items, the transcript text is sent to an AI service, without the audio or account data.
More: vocal remover · audio restoration · podcast mastering · music video for a track