Upload a recording and our AI turns the speech into a timed SRT subtitle file, plus VTT and a plain text transcript. Podcasts, interviews, lectures, voice-overs and the audio track of any video, in 60+ languages.
No software, no manual timing.
Choose your MP3, WAV, M4A or other recording and the language spoken in it.
Every sentence gets its exact start and end time and is cut into short subtitle lines.
Use the SRT in your video editor, on YouTube or in a player; the TXT is the full transcript.
interview-episode-12.mp3
MP3 · 38:42 · 2 speakers · English
1 00:00:01,080 --> 00:00:04,300 Thanks for coming on the show today. 2 00:00:04,620 --> 00:00:07,950 Happy to be here, I've been looking forward to this conversation.
The subtitles come from the sound, so the audio track alone gives exactly the same SRT. With the free tool FFmpeg: ffmpeg -i movie.mkv -vn -c:a libmp3lame -q:a 4 movie.mp3. The timing of the SRT still matches the video.
A 64–128 kbps MP3 is plenty. What matters is the voice: little background music, one person talking at a time, the microphone close to the speaker.
Choose the language that is spoken. For a recording that switches between languages, choose Multiple languages (auto-detect) and each sentence is written in its own language.
Translate the SRT into 80+ languages with the free Subtitle Translator, timestamps kept.
SRT is the subtitle format nearly every editor, player and video site reads: numbered lines with start and end times. VTT (WebVTT) is the same for web players and HTML5 video. TXT is the transcript without timing, for articles, notes and search. You get all three from one upload.
Verify your email to try it for free. After that, buy minutes once ($15 for 120 minutes) with PayPal or a card. One minute of audio uses one minute of credit, rounded up to the next full minute.
MP3, WAV, M4A, AAC, OGG, OPUS, FLAC, WMA and the audio of any video file (MP4, MOV, MKV, WebM...). There is nothing to convert first.
Long recordings are fine: podcasts, lectures and whole movies. Paid minutes have no limit on the file length.
Usually 90% to 100% on clear speech. Background music, overlapping voices and strong echo lower it. Fix any line afterwards in the Subtitle Studio.
More than 60 spoken languages, among them English, Spanish, Portuguese, French, German, Italian, Russian, Arabic, Hindi, Bengali, Indonesian, Vietnamese, Thai, Turkish, Chinese, Japanese and Korean.
Yes, with the 40 free minutes you get when you verify your email. After that you pay only for the minutes you use, with no subscription.
Yes. The audio track has the same timeline as the video, so every subtitle line lands at the right moment.
You get a TXT transcript with every job. For interviews and meetings see also Video transcription online.
They are private. Uploaded files are deleted automatically after 7 days; your SRT, VTT and TXT files stay in your account for a year.
40 free minutes when you verify your email. No credit card needed.
Upload audio