MP3 to text converter
Upload an MP3 and read it as text, with each speaker labelled. On the free plan you see the first 15 min of each file.
MP3 · M4A · WAV · FLAC · OGG · OGA · WebM · AAC · AMR · SPX · OPUS · MP4 · MOV · MKV
Free: read the first 15 min of each file · up to 5 h · 512 MB
Sample output
00:00 Maya Thanks for joining. Let's start with the launch date.
00:04 Daniel Design is done, but the store listing still needs screenshots.
00:10 Maya Can we have those by Friday?
00:13 Daniel Yes, if marketing sends the final copy tomorrow.
00:18 Priya I'll send it tonight.
00:21 Maya Great. Then the launch date stays where it is.
The team keeps the launch date. Design is finished, and the store screenshots will be ready by Friday once marketing sends the final copy, which Priya sends tonight.
- 00:00 Launch date
- 00:10 Store screenshots by Friday
- 00:18 Final copy tonight
1 00:00:00,000 --> 00:00:03,600 Maya: Thanks for joining. Let's start with the launch date. 2 00:00:04,000 --> 00:00:09,200 Daniel: Design is done, but the store listing still needs screenshots. 3 00:00:10,000 --> 00:00:12,100 Maya: Can we have those by Friday? 4 00:00:13,000 --> 00:00:17,400 Daniel: Yes, if marketing sends the final copy tomorrow. 5 00:00:18,000 --> 00:00:19,800 Priya: I'll send it tonight. 6 00:00:21,000 --> 00:00:24,500 Maya: Great. Then the launch date stays where it is.
- A transcript with timestamps and speaker labels you can rename
- Speech in 55 languages, or automatic language detection
- An AI summary and chapters you can jump between
- Download as TXT, SRT, VTT, Word (DOCX), with subtitles timed to the spoken words
- Video files too: only the audio track uploads
- Filler words and repeats removed or kept, your choice
Need the full recording?
- The whole transcript of every file, not only the first 15 min
- 50 h of file transcription a month, with no daily file limit
- Downloads of the whole transcript as TXT, SRT, VTT, Word (DOCX)
$15.99 a month, or $12.99 a month billed yearly
View Sync Pro plansHow it works
- Choose your MP3 file, up to 5 h and 512 MB.
- Set the spoken language or keep automatic detection, then press Transcribe.
- Open the MP3 transcript in your library when it is ready.
Getting a clean transcript from an MP3
MP3 is the format most podcasts, voice recorders and meeting apps hand you when you export audio, which is why it is the most common upload here. At normal quality settings it transcribes well. Files squeezed to a very low bitrate lose the crisp edges of consonants, and those are the sounds speech recognition relies on, so keep the export setting at its default rather than the smallest option.
There is no need to cut a long MP3 into parts: a whole file can run up to 5 h, as long as it stays under 512 MB. If an MP3 recorded in one room is over the size limit, export it again as mono. Keep stereo when each person was on their own channel, as in many call recordings: the uploader then offers one speaker per channel.
When you review the transcript, check names, product terms and figures against the audio first, since those are where any transcript is most likely to slip. Chapters help you find the stretch you need without replaying the whole recording.
Free vs Sync Pro
| Free | Sync Pro | |
|---|---|---|
| Readable transcript | First 15 min of each file | The whole transcript |
| Transcription hours | 6 h in total | 50 h of uploads a month |
| Files per day | Up to 10 | No daily file limit |
| Longest and largest file | 5 h · 512 MB | 5 h · 512 MB |
| Downloads | TXT, SRT, VTT, Word (DOCX), first 15 min | TXT, SRT, VTT, Word (DOCX) |
| Price | Free | $15.99 a month, or $12.99 a month billed yearly |
Questions
Can I convert a long MP3 to text?
Yes. An MP3 can be up to 5 h long and 512 MB, so most podcasts, lectures and meetings fit without splitting. On the free plan you read the first 15 min of the transcript.
Can I convert MP3 to text for free?
You can start free. Your account has 6 h of transcription in total, and each MP3 uses hours equal to its length. Free transcripts show the first 15 min; Sync Pro shows the whole file.
Does the MP3 transcript show who is speaking?
Yes. The transcript is split into speaker turns and each voice gets its own label, which you can see in the part of the transcript you can read. Labels are most reliable when people take turns rather than talk over each other.
Which MP3 settings work best?
The export defaults of most apps are fine. Avoid very low bitrates chosen to save space, because they blur consonants. Mono keeps a long single-microphone recording under the 512 MB limit, but leave a call in stereo if each side has its own channel.
MP3 to text converter
Choose a file