Audio to SRT
Drop a voiceover, podcast or recording and get an SRT file of everything that's said, with timing. It's transcribed in your browser, so the audio stays on your device.
Transcribed on your device by an AI speech model. Your file is never uploaded.
Subtitles in three steps
Drop your audio
MP3, WAV, M4A, AAC, FLAC or OGG, up to 30 minutes.
Pick the language
Or leave it on automatic detection.
Generate and download
Check the text, then download the .srt.
When you need subtitles from audio
Recording the voiceover separately from the video is common: the SRT made from it lines up with the final video as long as the voiceover starts at the same moment. If it doesn't, move the whole file with the SRT time shift tool.
Podcasters use the SRT for audiogram clips and YouTube uploads, and as a quick transcript to search. Subtitles are split into lines of up to 42 characters and two lines per subtitle; change the line length before you run it.
How the transcription works
Transcription is done by Whisper, the open-source speech recognition model from OpenAI, running inside your browser. The model downloads once (40 to 250 MB depending on the accuracy you pick) and is cached, so later files start straight away. Your video is never uploaded.
With a recent Chrome or Edge on a computer with a graphics card, it runs on the GPU and takes a fraction of the video's length. Without one it runs on the CPU, which can take about as long as the video itself. Files up to 30 minutes work.
Whisper understands about 100 languages and adds punctuation. Accuracy is good on clear speech, and lower with music, heavy accents or several people talking at once: check names and numbers before you publish.
Frequently
Asked Questions
Can I convert MP3 to SRT?
Yes. Drop the MP3 and the speech in it is transcribed into a timed SRT file.
Is my audio uploaded?
No. The speech model runs in your browser.
Why do the times not match my video?
The audio probably starts at a different point than the video. Shift the subtitles by the difference with the SRT time shift tool.
Which accuracy should I pick?
Balanced suits most clear recordings. Use Best for accents, noisy recordings or names, if you can wait longer.