Transcribe audio to text on your phone
To transcribe audio to text on your phone, record or import the audio in Voicence, pick the language being spoken, and tap transcribe. The text comes back within a few minutes, split by speaker, and you can correct it and export a PDF. The transcription step needs an internet connection.
Free to start. For Android and iPhone.
Are we locking the presentation outline today?
Yes. We just need to double-check the quarterly sales numbers.
Then I'll check them by Thursday and you put the slides together.
Step by step
-
Record or import the audio
Record in the app, or import an audio file (MP3, M4A, WAV, OGG/Opus) or an MP4 video. With video, only the audio is used.
-
Pick the language
Choose the language spoken in the recording. The app transcribes in the language you select, so this choice matters.
-
Tap transcribe
The audio is sent for processing and the text comes back within a few minutes. You need to be online for this part.
-
Fix what it got wrong
Tap any line to hear that moment, then correct the text. Rename the speakers so each line shows who said it.
-
Export or share
Build a PDF with the transcript, the summary, and your notes, or copy the summary text and paste it where you need it.
Where the audio can come from
You don't have to record inside the app. Anything you already have on your phone works as long as it is in a supported format.
- A new recording made in the app, with pause and resume
- An audio file: MP3, M4A, WAV, or OGG/Opus
- A voice memo saved to your phone's files
- An MP4 video, such as a screen recording or a clip from your camera roll
- A YouTube link, which imports the audio only
- A WhatsApp voice message
How to get a better transcript
Speech to text is only as good as the audio it hears. Most errors come from noise, distance, and people talking over each other, and you can control all three before you hit record.
Even with clean audio, expect mistakes on proper names, acronyms, and technical terms. Read the transcript once before you rely on it or send it to anyone.
- Record somewhere quiet. Fans, traffic, and background music all end up in the text as errors.
- Keep the phone close to whoever is talking, with the microphone uncovered.
- Have one person speak at a time. Overlapping voices are the hardest thing to transcribe.
- Select the language that is actually spoken. The wrong language produces text that makes no sense.
What to do with the text afterward
Every transcript comes with an automatic summary: a short paragraph with the gist, then Key points, Action items with the person responsible, and Topics. Tap a topic to hear that part of the recording.
The summary is written in the language of the recording, and you can ask for a translation of the summary into another language. The transcript itself is not translated.
From the same transcript you can generate a Quiz or Flashcards, add your own Notes, and export a PDF. You choose what goes in the PDF: transcript, summary, notes, or any mix of the three.
What it costs to transcribe audio to text
Downloading the app, recording, and listening are free. Transcription costs 1 coin per minute of audio. The summary, quiz, and flashcards don't use coins.
You earn coins by watching video ads, and you get a bonus when you sign in with Google on Android or Apple on iPhone. Coin packs are also sold in the app. Signing in is optional.
On the free plan, each audio can be from 10 seconds to 60 minutes long. Premium removes ads, raises the length limit, and adds bonus coins at each renewal.
What the app does not do
A few limits are worth knowing before you start, so you don't plan around something that isn't there.
- It does not transcribe offline. Only recording and playback work without internet.
- It does not export TXT, DOCX, or subtitle files. You get a PDF, or you copy and share text.
- It has no web or desktop version. It runs on Android 7.0 or later and on iPhone and iPad with iOS 16 or later.
- It does not sync or back up recordings between devices.
Frequently asked questions
Can I turn an iPhone voice memo into text?
Yes. Save the voice memo to Files, then import it in the app. Voice memos are M4A files, which is a supported format.
Is voice to text free?
Recording and listening are free. Transcription costs 1 coin per minute of audio, and you can earn coins by watching video ads instead of buying them.
How long can the audio be?
On the free plan, between 10 seconds and 60 minutes per audio. Premium allows longer audio per transcription.
Which languages can it transcribe?
Dozens, including English, Spanish, Portuguese, French, German, Italian, Dutch, Russian, Japanese, Korean, Chinese, Arabic, Hindi, and Turkish.
Do I need an account?
No. You can record and transcribe without signing in. Signing in with Google or Apple is optional.