FLAC to text
A FLAC file is accepted as it is: the recording goes up, the words come back with a start and an end time on every line. Lossless sound needs no conversion step first. One file is up to 64 MB and 120 minutes, the free plan is $0, Pro costs $10 a month paid yearly.
The size limit is the part that matters
FLAC keeps everything the microphone captured, so a FLAC of the same meeting is normally a bigger file than a compressed recording of that meeting. The service does not care — it reads the container it is given. The one number to watch is 64 MB, because a lossless file reaches it sooner than a small compressed one. If your FLAC is over the limit, the ways out are simple: trim the recording, split it into parts, or keep the FLAC as the archive and upload a smaller copy for the transcript.
| The question | The answer | Where the number comes from |
|---|---|---|
| Is FLAC accepted? | yes — flac is named in the accept list of the upload field | transcrib.si/index.html, checked |
| How large may one file be? | 64 MB | transcrib.si/pricing.html, checked |
| How long may one file be? | 120 minutes on Pro and Team, 30 minutes on the free plan | transcrib.si/pricing.html, checked |
| How many files a day on the free plan? | 3 | transcrib.si/pricing.html, checked |
| What does the free plan cost? | $0, and no card is asked for | transcrib.si/pricing.html, checked |
| What does Pro cost? | $10 a month paid yearly ($120 a year), or $20 a month paid monthly | transcrib.si/pricing.html, checked |
| How much audio does Pro cover a month? | 1,500 minutes of fair use | transcrib.si/pricing.html, checked |
What happens between the upload and the text
- The file arrives and is checked against the two limits: 64 MB and 120 minutes.
- The sound is written down. The answer comes as segments, each with the second it starts and the second it ends.
- If you asked for speakers, each segment is marked with the voice it belongs to — the same request that the meeting guide describes in detail.
- The transcript is saved in your account, and you take it away in TXT, Markdown, SRT, VTT or CSV, and in DOCX if you are on Pro.
The engine is our own, with a profile tuned for Russian speech and for the Russian-English mix. Russian and English are the two languages it recognizes; you can set the language or leave it on automatic detection.
Where the file is processed
A recording in Russian is processed on our own infrastructure, which sits outside the United States. A file that is entirely in English can go to a third-party cloud speech provider in the United States when that fallback is enabled on the server. The audio is used to produce the transcript and to run the service; it is never sold and never used to train models for other customers. A file you delete leaves the live system at once and the encrypted backups within 30 days. The privacy policy has the details, the security page has the storage story.
When a FLAC is the wrong file to upload
- A very long lossless recording. Two hours of FLAC will usually cross 64 MB before it crosses 120 minutes. Split it, or upload a compressed copy for the text.
- A file with no speech in it. Music, a door closing, a cough — the transcript will be empty or nearly so, and that is what the recording contains.
- A file you have already compressed twice. Lossy compression of a lossless file loses more than it saves. If the FLAC exists, send the FLAC.
Other containers, the same result
The upload field of the site names ten containers: mp3, wav, m4a, mp4, webm, ogg, flac, aac, wma and mov. Each of them goes through the same pipeline, so an MP3 and a FLAC of the same hour give the same text, the same timecodes and the same exports. If you work with a different format every week, the general guide lists them all.
Put a file on the page and read the first lines.
The widget below is the same one as on the home page: file → transcript with timecodes and speakers → export. The transcript is saved to your account.
Drop an audio or video file
or — mp3, wav, m4a, mp4, up to 64 MB and two hours
Transcription runs under your account: sign in or create a free account.
No account yet? The free plan needs no card. Create a free account or sign in.
Questions this page answers.
Do I have to convert a FLAC before uploading it?
No. The upload field lists flac among the accepted containers, so the file goes up exactly as it was recorded.
Why does my FLAC hit the size limit first?
Lossless audio keeps everything the microphone captured, so the file is larger than a compressed recording of the same meeting, and the 64 MB limit arrives sooner than the 120-minute one.
Can I get the speakers separated in a FLAC?
Yes. Speaker labels are part of every plan, including the free one — switch on “Split by speaker” and each line carries the voice it belongs to.
Which languages are recognized?
Russian and English. Leave the language on automatic detection or set it yourself; the transcript states which one was used.
What happens to a FLAC I upload?
It is used to produce the transcript and to run the service, it is never sold, and it is never used to train models for other customers. Delete it and it leaves the live system immediately.
Related pages.
The compressed container next door.
A Matroska video, sound only.
How to split a file that is too big.
What our engine does with Russian speech.
How seven services split the voices.
Plans, limits and fair use.
Mark Burmistrov, Founder.
Every number on this page comes from the service contract, the pricing page or our own measurements. The author of the page and the publisher of the site are the same person. Questions and corrections: support@transcrib.si.