Audio to text with timestamps — every line tied back to the recording
A transcript without timestamps is a wall of text you cannot check. LoroNote timestamps the transcript at sentence level, highlights the current line while the audio plays, and lets you tap any line to jump straight to that moment in the recording. Export keeps the timing: TXT for the text, SRT when the timecodes need to travel with it. All of it runs on the device.
- Granularity
- Sentence level
- In the app
- Tap a line to replay it
- Export
- SRT carries the timecodes
- With speakers
- Labels and times together
- Price
- Free download · $39.99 lifetime
How to get a timestamped transcript
- 1
Install LoroNote and open it
The download is free and no account is created — there is no sign-up screen, because there is no server holding your transcripts.
- 2
Tap Import File
Import the recording, or record inside the app — timestamps are produced either way, for audio and for the audio track of a video.
- 3
Confirm the language
LoroNote detects the spoken language automatically and supports over 100. If the recording is full of names, product codes, or jargon, add them to the custom dictionary first so they come back spelled correctly.
- 4
Let it transcribe on the device
Whisper Large V3 Turbo runs on the phone or iPad itself — airplane mode changes nothing. Keep the app open while a long file processes; it uses the device GPU and pausing it costs you time.
- 5
Review the speakers, then export
Play the transcript back with the current line highlighted, tap any sentence to hear it, correct what needs correcting, then export SRT to keep the timecodes or TXT for the plain text.
Why the timing is the part that matters
Timestamps are what turn a transcript from a rough record into something you can rely on in public:
- Quoting an interview accurately — you can hear the exact line again before you publish it
- Finding the decision inside a two-hour meeting without scrubbing the audio
- Citing a lecture at a specific minute in your notes or a paper
- Correcting a misheard name: tap the line, listen, fix it, carry on
- Handing a timed file to an editor, a captioner, or a colleague who needs to verify it
How long it takes
The timestamps are produced as part of transcription, so they cost nothing extra in time:
| Recording length | Time to transcribe |
|---|---|
| 5 minutes | about 16 seconds |
| 30 minutes | about 1.5 minutes |
| 1 hour | about 3 minutes |
| 3 hours | about 10 minutes |
Measured by LoroNote on an iPhone 15 Pro at roughly 19x real time. Newer devices transcribe faster; older supported models take longer.
How the timing behaves
Sentence level, not word level
Each line carries its own start time. Individual words are not separately timestamped, which is the right granularity for quoting and navigation and the wrong one for karaoke-style captions.
SRT is where the timecodes live
Export as SRT and every line arrives in standard hh:mm:ss,mmm form that any caption tool, player, or editor reads. TXT export is for when you want the words and nothing else.
Speaker labels and timestamps travel together
An exported interview tells you who said something and when, which is the combination that makes a transcript quotable rather than merely searchable.
Editing does not cut the transcript loose from the audio
You can rewrite a line while the original recording plays and still tap it afterwards to hear the moment it came from.
Timestamps are only useful if you still have the audio
The whole value of a timecode is that it points at something you can play. That is an argument for keeping the recording and the transcript in the same place — on the device — rather than splitting them between a phone and a service that holds the audio for as long as its retention policy says.
It is also why the offline part matters here. Checking a quote against the recording is something you do at a desk at midnight, on a train, or in a courtroom corridor. A player that needs a connection to fetch the audio is a player that fails exactly when you are checking a fact under deadline.
Common questions
Does LoroNote give word-level timestamps?
No — timestamps are at sentence level. Every line has its own start time, which is what navigation, quoting, and standard subtitles need. Word-by-word timing for animated captions is not something LoroNote produces.
How do I export a transcript with timestamps?
Export as SRT. It writes each line with standard hh:mm:ss,mmm timecodes and keeps speaker labels attached, so the file works both as a subtitle track and as a timed transcript.
Can I jump to a moment in the recording from the transcript?
Yes. Tap a line and playback moves to that point, with the current line highlighted as the audio runs. This is also the fastest way to fix a misheard name — listen to the source rather than guessing.
Do timestamps work on imported files as well as new recordings?
Yes. An imported MP3, WAV, M4A, MP4, or MOV is timestamped exactly like something recorded in the app, because the timing comes from the transcription pass rather than from the recorder.
Does any of this need an internet connection?
No. Transcription, timestamping, speaker labels, and playback all run on the device. The transcript and the audio it points at are both stored locally, so nothing breaks offline.
Related
- Subtitle generator (SRT) Timed .srt files from audio or video, with speaker labels, generated on the device.
- Video to text MP4 and MOV: the audio track is read straight out of the file, no editor export first.
- MP3 to text Podcasts, dictaphone exports, and webinar audio, transcribed without an upload or a minute cap.
Check a quote against the audio
Transcribe one interview, tap the line you were about to publish, and listen to what was actually said.
Download LoroNote