MP3 to text
Drop in an MP3 and get a transcript. Free and unlimited in your browser, or fast with speaker labels when you are short on time.
How to convert an MP3 to text
- Open Skeleton Fingers. There is nothing to install, and the free lane does not need an account.
- Choose a lane. "In your browser" is free and keeps the file on your device. "Fast" runs on our servers with speaker labels.
- Drop in your MP3. No conversion needed.
- Read the transcript. Check names and numbers against the audio if you plan to quote it.
The two lanes
| Detail | In your browser | Fast |
|---|---|---|
| Price | Free, unlimited | Free for files up to 30 minutes, 3 a day, then $5 for 3 hours or Pro |
| Where it runs | Your device (Whisper) | Our servers |
| Speed | Depends on your computer | Your browser converts and uploads the audio (about 115 MB per hour), then our servers transcribe it in seconds; total time varies with your device and connection |
| Speaker labels | No | Yes |
| Account | Not needed | Free account |
| Your MP3 | Never leaves your device | Uploaded and stored with your account until you delete it |
The first time you use the browser lane, it downloads the speech model once. The fast lane also detects the spoken language automatically.
What affects MP3 transcription quality
MP3 is a compressed format, but the compression is rarely the problem. A spoken-word MP3 at an ordinary bitrate carries plenty of detail for transcription. What matters far more is how the audio was recorded:
- Distance from the microphone. Voices close to the mic transcribe well; voices across a room do not.
- Background noise. Music, traffic, fans and chatter all compete with speech.
- Overlapping speech. When people talk over each other, any transcriber struggles.
- Repeated re-encoding. An MP3 that has been converted several times, or recorded off a phone speaker, loses clarity each time. Use the original file when you have it.
Where MP3 files come from
Podcast episodes, audiobook samples, call recordings, digital voice recorders, downloaded lectures and exported interviews are all commonly MP3. If you have a different format, Skeleton Fingers also handles M4A, WAV and video files, so you rarely need a converter.
What it costs
The browser lane is always free. On the fast lane, minutes are counted by the length of the audio: a free account transcribes files up to 30 minutes free, 3 a day, longer files use pack hours for their full length, an hour pack is $5 for 3 fast hours that never expire, and Pro is $9.99 a month for 10 fast hours. No subscription is required.
Frequently asked questions
Is MP3 to text free?
Yes. The in-your-browser lane converts MP3 to text free, with no limit and no account. The fast lane is free with a free account for files up to 30 minutes, 3 a day.
Do I have to upload my MP3?
Not on the browser lane. It transcribes on your device and the file never leaves it. The fast lane uploads the file to our servers.
How long does a one hour MP3 take?
On the fast lane, your browser converts the MP3, uploads the audio (about 115 MB per hour), and our servers transcribe it in seconds. The first two steps depend on your device and connection, so the total time varies. On the browser lane, it depends on your computer.
Can it tell different speakers apart?
The fast lane labels speakers. The browser lane gives you the words without speaker labels.
Convert your MP3 to text
Free in your browser. Fast when you need it. No subscription required.
Transcribe free